Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision

Monday 4 May

Computer Vision

AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion

Yu-Ju Tsai, Brian Price, Qing Liu et al. (+5 more)

Personalized image completion aims to restore occluded regions in personal photos while preserving identity and appearance. Existing methods either rely on generic inpainting models that often fail to maintain identity consistency, or assume that suitable reference images are explicitly provided. In practice, suitable references are often not explicitly provided, requiring the system to search for identity-consistent images within personal photo collections. We present AlbumFill, a training-free framework that retrieves identity-consistent references from personal albums for personalized completion. Given an occluded image and a personal album, a vision-language model infers missing semantic cues to guide composed image retrieval, and the retrieved references are used by reference-based completion models. To facilitate this task, we introduce a dataset containing 54K human-centric samples with associated album images. Experiments across multiple baselines demonstrate the difficulty of personalized completion and highlight the importance of identity-consistent reference retrieval. Project Page: https://liagm.github.io/AlbumFill/
Read the full abstract

All authors Yu-Ju Tsai, Brian Price, Qing Liu, Luis Figueroa, Daniil Pakhomov, Zhihong Ding, Scott Cohen, Ming-Hsuan Yang

Computer Vision

Laplacian Frequency Interaction Network for Rural Thematic Road Extraction

Baiyan Chen and Weixin Zhai

Rural thematic road network construction aims to extract topological road structures from movement trajectory images of agricultural machinery. However, this task faces challenges where downsampling methods commonly used in existing studies tend to blur the sparse high-frequency road structures, and the heavy noise from dense field operations often leads to fragmented or redundant topologies in the extracted networks. To address these challenges, we propose LFINet, a Laplacian Frequency Interaction Network. The network begins with a Laplacian Multi-scale Separator (LMS) to decouple the image into low-frequency semantic contexts and high-frequency structural details. These components are then processed by the Cross-Frequency Interaction Block (CFIB) through a dual-pathway architecture in which a High-Frequency Block (HFB) refines local structures while a Spatial Transformer (ST) captures global semantics. Subsequently, a Frequency Gated Modulation (FGM) mechanism integrates the features from pathways by leveraging semantic contexts to calibrate the structural details. Finally, a Progressive Reconstruction Decoder iteratively fuses multi-scale features to ensure topological consistency. Experiments conducted on a real-world agricultural trajectories dataset from Henan Province, China, show that LFINet establishes a new state-of-the-art. Specifically, it achieves an F1-score of 92.54% and an IoU of 86.12%, surpassing the second-ranked method by 0.64% and 1.1%, respectively. This confirms its capability to effectively construct topological road networks from noisy and sparse field data.
Read the full abstract

Computer Vision

Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions

Fadeel Sher Khan, Long N. Le, Abhinau K. Venkataramanan et al. (+2 more)

Traditional image quality assessment (IQA) methods rely on mean opinion scores (MOS), which are resource-intensive to collect and fail to provide interpretable, localized feedback on specific image distortions. We overcome these limitations by shifting from absolute quality prediction to a relational and directional assessment. Our approach utilizes a self-supervised synthetic distortion engine to generate training data, eliminating the need for manual annotation. A distortion prediction network is trained with an anti-symmetric objective to produce spatially-aware, disentangled maps that identify the type, intensity, and direction of distortions relative to a reference image. Subsequently, a scoring network is trained via contrastive learning on ordinally ranked image sets to predict a relational quality score. Our method provides a more granular and interpretable approach to IQA for the targeted optimization of image processing algorithms without requiring any human-labeled quality scores.
Read the full abstract

All authors Fadeel Sher Khan, Long N. Le, Abhinau K. Venkataramanan, Seok-Jun Lee, Hamid R. Sheikh

Computer Vision

Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion

Amirhosein Javadi, Shirin Saeedi Bidokhti and Tara Javidi

Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling the generative process using highly compact conditioning signals. In this work, we present ActDiff-VC, a diffusion-based video compression framework for the ultra-low-bitrate regime. Our method partitions videos into variable-length segments, transmits keyframes only when needed, and summarizes temporal dynamics using a compact set of tracked point trajectories. Conditioned on these sparse signals, a conditional diffusion decoder synthesizes the remaining frames, enabling perceptually realistic reconstruction under severe rate constraints. To support this design, we introduce two mechanisms: content-adaptive keyframe selection and budget-aware sparse trajectory selection, which together enable compact yet effective conditioning for generative reconstruction. ActDiff-VC has an asymmetric computational profile: on a single NVIDIA A100 GPU, encoding requires 109 ms per frame, while the adopted 20-step diffusion decoder requires 2311 ms per frame, making the framework particularly suitable for ultra-low-bitrate applications such as cloud-assisted reconstruction, archival storage, and offline content distribution, where lightweight encoding and perceptual reconstruction quality are prioritized. Experiments on the UVG and MCL-JCV benchmarks show that ActDiff-VC achieves up to 64.6% bitrate reduction at matched NIQE, improves KID by up to 64.6% and FID by up to 37.7% at comparable bitrates against strong learned codecs, and delivers favorable perceptual rate–distortion trade-offs relative to learned and generative baselines in the ultra-low-bitrate regime. A human study with 147 participants further supports these perceptual gains, with ActDiff-VC preferred over DCVC-FM in 62.6% of pairwise comparisons.
Read the full abstract

Computer Vision

VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition

Tanush Yadav, Mohammadreza Salehi, Jae Sung Park et al. (+6 more)

Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understanding. Unfortunately, due to a lack of sufficiently diverse and challenging data, modern vision-language models (VLMs) are no longer evaluated on their action recognition capabilities. To revitalize action recognition in the era of VLMs, we advocate for a returned focus on domain-specific actions. To this end, we introduce VideoNet, a domain-specific action recognition benchmark covering 1,000 distinct actions from 37 domains. We begin with a multiple-choice evaluation setting, where the difference between closed and open models is stark: Gemini 3.1 Pro attains 69.9% accuracy while Qwen3-VL-8B gets a mere 45.0%. To understand why VLMs struggle on VideoNet, we relax the questions into a binary setting, where random chance is 50%. Still, Qwen achieves only 59.2% accuracy. Further relaxing the evaluation setup, we provide $k\in\{1,2,3\}$ in-context examples of the action. Some models excel in the few-shot setting, while others falter; Qwen improves $+7.0\%$, while Gemini declines $-4.8\%$. Notably, these gains fall short of the $+13.6\%$ improvement in non-expert humans when given few-shot examples. Finding that VLMs struggle to fully exploit in-context examples, we shift from test-time improvements to the training side. We collect the first large-scale training dataset for domain-specific actions, totaling nearly 500k video question-answer pairs. Fine-tuning a Molmo2-4B model on our data, we surpass all open-weight 8B models on the VideoNet benchmark.
Read the full abstract

All authors Tanush Yadav, Mohammadreza Salehi, Jae Sung Park, Vivek Ramanujan, Hannaneh Hajishirzi, Yejin Choi, Ali Farhadi, Rohun Tripathi, Ranjay Krishna

Computer Vision

IConFace: Fine-Grained Identity Conditioning for Reference-Aware Face Restoration

Axi Niu, Jinyang Zhang and Senyan Qing

Severe face degradation can remove person-specific evidence, making restoration underdetermined. A generative prior may recover a sharp, plausible face yet miss localized traits that persist across images of the same person. Same-identity references supply this missing evidence, while the degraded observation anchors target structure. We propose IConFace, a fine-grained identity-conditioned framework that optionally conditions restoration on up to three same-identity references. Its hybrid concat backbone retains degraded and reference observations as dense visual tokens, preserving localized reference evidence. An identity pathway provides compact multi-reference guidance, while a degraded-structure pathway injects full-field and local-residual memories to reinforce target-aligned structure. We also introduce a human-audited benchmark that measures whether persistent localized identity details survive restoration. IConFace achieves leading reference compatibility, especially under severe degradation, and the highest observed preservation rate on this benchmark. Without references, it achieves leading learned perceptual quality across five blind-restoration benchmarks. Joint reference-based and paired-target evaluations show that reference-supported identity recovery and exact target agreement are complementary.
Read the full abstract

Computer Vision

Edge-Efficient Image Restoration: Transformer Distillation into State-Space Models

Srinivas Soumitri Miriyala, Sowmya Vajrala, Sravanth Kodavanti et al. (+2 more)

We propose a modular framework for hybrid image restoration that integrates transformer and state-space model (SSM) blocks with a focus on improving runtime efficiency on edge hardware. While transformers provide strong global modeling through self-attention, their attention kernels incur substantial latency on mobile devices, especially for high-resolution inputs. In contrast, SSMs such as Mamba offer lineartime sequence modeling with lower runtime overhead but may underperform on fine grained restoration tasks. To balance accuracy and efficiency, we train lightweight SSM blocks as feature-distilled surrogates of transformer blocks and use them to construct hybrid U-Net-style architectures. To automatically discover effective block combinations, we introduce Efficient Network Search (ENS), a multi-objective search strategy that selects task-specific hybrid configurations from pre-aligned components. ENS optimizes restoration quality while penalizing transformer usage, serving as a lightweight proxy for latency and enabling architecture discovery without repeated hardware profiling. On a Snapdragon 8 Elite CPU, the Restormer baseline requires 10119.52 ms for inference. In contrast, ENS-discovered hybrids significantly reduce runtime: ENS-Deblurring runs in 2973 ms (3.4x faster), ENS-Deraining in 5816 ms (1.74x faster), and ENS-Denoising in 8666 ms (1.17x faster), while maintaining competitive restoration quality.
Read the full abstract

All authors Srinivas Soumitri Miriyala, Sowmya Vajrala, Sravanth Kodavanti, Vikram Nelvoy Rajendiran, Sharan Kumar Allur

Computer Vision

HumanSplatHMR: Closing the Loop Between Human Mesh Recovery and Gaussian Splatting Avatar

Yeheng Zong, Pou-Chun Kung, Yike Pan et al. (+4 more)

Accurately recovering human pose and appearance from video is an essential component of scene reconstruction, with applications to motion capture, motion prediction, virtual reality, and digital twinning. Despite significant interest in building realistic human avatars from video, this paper demonstrates that existing methods do not accurately recover the 3D geometry of humans. ViT-based approaches are not consistently reliable and can overfit to 2D views, while NeRF- and Gaussian Splatting-based avatars treat pose and appearance separately, limiting rendering generalization to new poses. To resolve these shortcomings, this paper proposes HumanSplatHMR, a joint optimization framework that refines 3D human poses while simultaneously learning a high-fidelity avatar for novel-view and novel-pose synthesis. Our key insight is to close the loop between geometric pose estimation and differentiable rendering. Unlike prior human avatar methods that rely on accurate human pose obtained through motion capture systems or offline refinement, which are impractical in in-the-wild scenarios, our approach uses only human mesh estimates from a state-of-the-art human pose estimator to better reflect real-world conditions. Therefore, instead of using the human pose only as a deformation prior, HumanSplatHMR backpropagates photometric, segmentation, and depth losses through a differentiable renderer to the pose parameters and global position. This coupling refines the global 3D pose over time, improving accuracy and alignment while producing better renderings from novel views. Experiments show consistent improvements over pose recovery baselines that omit image-level refinement and avatar baselines that decouple pose estimation from avatar reconstruction.
Read the full abstract

All authors Yeheng Zong, Pou-Chun Kung, Yike Pan, Seth Isaacson, Yizhou Chen, Ram Vasudevan, Katherine A. Skinner

Computer Vision

Linearizing Vision Transformer with Test-Time Training

Yining Li, Dongchen Han, Zeyu Liu et al. (+3 more)

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained Transformers provides an appealing shortcut, yet the fundamental representational gap between Softmax and linear attention prevents effective weight transfer. In this work, we address this conversion challenge from two perspectives: architectural alignment and representational alignment. We identify Test-Time Training (TTT) as a linear-complexity architecture whose two-layer dynamic formulation is structurally aligned with Softmax attention, enabling direct inheritance of pretrained attention weights. To further align representational properties, including key shift-invariance and locality, we introduce key instance normalization and a lightweight locality enhancement module. We validate our approach by linearizing Stable Diffusion 3.5 and introduce SD3.5-T$^5$ (Transformer To Test Time Training). With only 1 hour of fine-tuning on 4$\times$H20 GPUs, SD3.5-T$^5$ achieves comparable text-to-image quality to the fine-tuned Softmax model, while accelerating inference by 1.32$\times$ and 1.47$\times$ at 1K and 2K resolutions. Code is available at https://github.com/LeapLabTHU/Transformer-to-TTT.
Read the full abstract

All authors Yining Li, Dongchen Han, Zeyu Liu, Hanyi Wang, Yulin Wang, Gao Huang

Computer Vision

TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution

Sowmya Vajrala, Akshay Bankar, Manjunath Arveti et al. (+5 more)

Diffusion models have recently demonstrated strong performance for image restoration tasks, including super-resolution. However, their large model size and iterative sampling procedures make them computationally expensive for practical deployment. In this work, we present TOC-SR, a framework for building efficient one-step super-resolution models by first discovering a compact diffusion backbone. Starting from a sixteen-channel latent diffusion model, we construct parameter-efficient surrogate blocks using feature-wise generative distillation and perform architecture discovery using epsilon-constrained Bayesian Optimization to minimize model complexity while preserving generative fidelity. The resulting compact diffusion backbone achieves a 6.6x reduction in parameters and a 2.8x reduction in GMACs compared to the expanded diffusion model. We then adapt this backbone for super-resolution and distill the diffusion process into a single-step generator. Experiments demonstrate that the proposed approach enables efficient super-resolution while maintaining strong reconstruction quality.
Read the full abstract

All authors Sowmya Vajrala, Akshay Bankar, Manjunath Arveti, Shreyas Pandith, Sravanth Kodavanti, Subhajit Sanyal, Amit Unde, Srinivas Soumitri Miriyala

Computer Vision

FoR-Net: Focus-on-Regions Network for Semantic Segmentation

Sheng-Wei Chan, Hsin-Jui Pan and Jen-Shiun Chiang

This paper presents Focus-on-Regions Network (FoR-Net), an efficient semantic segmentation framework that explicitly focuses on hard regions through a selector-driven Top-K mechanism. Instead of relying on heavy global modeling, FoR-Net selectively enhances structurally informative regions. Multi-scale reasoning branches are introduced to aggregate spatial context efficiently. Experiments on the Cityscapes dataset demonstrate that FoR-Net achieves competitive performance while maintaining a lightweight architecture.
Read the full abstract

Computer Vision

Unified Map Prior Encoder for Mapping and Planning

Zongzheng Zhang, Sizhe Zou, Guantian Zheng et al. (+12 more)

Online mapping and end-to-end (E2E) planning in autonomous driving remain largely sensor-centric, leaving rich map priors, including HD/SD vector maps, rasterized SD maps, and satellite imagery, underused because of heterogeneity, pose drift, and inconsistent availability at test time. We present UMPE, a Unified Map Prior Encoder that can ingest any subset of four priors and fuse them with BEV features for both mapping and planning. UMPE has two branches. The vector encoder pre-aligns HD/SD polylines with a frame-wise SE(2) correction, encodes points via multi-frequency sinusoidal features, and produces polyline tokens with confidence scores. BEV queries then apply cross-attention with confidence bias, followed by normalized channel-wise gating to avoid length imbalance and softly down-weight uncertain sources. The raster encoder shares a ResNet-18 backbone conditioned by FiLM with scaling and shift at every stage, performs SE(2) micro-alignment, and injects priors through zero-initialized residual fusion, so the network starts from a do-no-harm baseline and learns to add only useful prior evidence. A vector-then-raster fusion order reflects the inductive bias of geometry first, appearance second. On nuScenes mapping, UMPE lifts MapTRv2 from 61.5 to 67.4 mAP (+5.9) and MapQR from 66.4 to 71.7 mAP (+5.3). On Argoverse2, UMPE adds +4.1 mAP over strong baselines. UMPE is compositional: when trained with all priors, it outperforms single-prior models even when only one prior is available at test time, demonstrating powerset robustness. For E2E planning with the VAD backbone on nuScenes, UMPE reduces trajectory error from 0.72 to 0.42 m L2 on average (-0.30 m) and collision rate from 0.22% to 0.12% (-0.10%), surpassing recent prior-injection methods. These results show that a unified, alignment-aware treatment of heterogeneous map priors yields better mapping and better planning.
Read the full abstract

All authors Zongzheng Zhang, Sizhe Zou, Guantian Zheng, Zhenxin Zhu, Yu Gao, Guoxuan Chi, Shuo Wang, Yuwen Heng, Zhigang Sun, Yiru Wang, Hao Sun, Chao Ma, Zhen Li, Anqing Jiang, Hao Zhao

Computer Vision · Cross-listed from cs.RO

DynoSLAM: Dynamic SLAM with Generative Graph Neural Networks for Real-World Social Navigation

Danil Tokhchukov, Veronika Morozova and Gonzalo Ferrer

Traditional Simultaneous Localization and Mapping (SLAM) algorithms rely heavily on the static environment assumption, which severely limits their applicability in real-world spaces populated by moving entities, such as pedestrians. In this work, we propose DynoSLAM, a tightly-coupled Dynamic GraphSLAM architecture that integrates socially-aware Graph Neural Networks (GNNs) directly into the factor graph optimization. Unlike conventional approaches that use rigid constant-velocity heuristics or deterministic single-agent neural priors, our framework formulates pedestrian motion forecasting as a stochastic World Model. By utilizing Monte Carlo rollouts from a trained GNN, we capture the multimodal epistemic uncertainty of human interactions and embed it into the SLAM graph via a dynamic Mahalanobis distance factor. We demonstrate through extensive simulated experiments that this stochastic formulation not only maintains highly accurate retrospective tracking but also prevents the optimization failures caused by the deterministic "argmax problem". Ultimately, extracting the empirical mean and covariance matrices of future pedestrian states provides a mathematically rigorous, probabilistic safety envelope for downstream local planners, enabling anticipatory and collision-free robot navigation in densely crowded environments.
Read the full abstract

Computer Vision

Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation

Chenyu Hui, Xiaodi Huang, Siyu Xu et al. (+5 more)

Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often suffers from a substantial visual domain gap and limited environmental diversity, resulting in weak real-world generalization. We present an efficient video augmentation framework that converts simulated VLA videos into realistic training videos while preserving task semantics and action trajectories. Our pipeline extracts structured conditions from simulation via video semantic segmentation and video captioning, rewrites captions to diversify environments, and uses a conditional video transfer model to synthesize realistic videos. To make augmentation practical at scale, we introduce a diffusion feature-reuse mechanism that reuses video tokens across adjacent timesteps to accelerate generation, and a coreset sampling strategy that identifies a compact, non-redundant subset for augmentation under limited computation. Extensive experiments on Robotwin 2.0, LIBERO, LIBERO-Plus, and a real robotic platform demonstrate consistent improvements. For example, our method improves RDT-1B by 8% on Robotwin 2.0, and boosts $\pi_0$ by 5.1% on the more challenging LIBERO-Plus benchmark. Code is available at: https://github.com/nanfangxiansheng/Seeing-Realism-from-Simulation.
Read the full abstract

All authors Chenyu Hui, Xiaodi Huang, Siyu Xu, Yunke Wang, Shan You, Fei Wang, Tao Huang, Chang Xu

Computer Vision

Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting

Giacomo Pacini, Luca Ciampi, Nicola Messina et al. (+3 more)

Open-world text-guided class-agnostic counting (CAC) has emerged as a flexible paradigm for counting arbitrary object classes by using natural language prompts. However, current evaluation protocols primarily focus on standard counting errors within single-category images, overlooking a fundamental requirement: the ability to correctly ground the textual prompt in the visual scene. In this paper, we show that several state-of-the-art CAC models often struggle to determine which object class should be counted based on the given prompt, revealing a misalignment between textual semantics and visual object representations. This limitation leads to spurious counting responses and reduced reliability in real-world scenarios. To systematically address these limitations, we propose a new evaluation framework focused on model robustness and trustworthiness. Our contribution is two-fold: (i) we introduce PrACo++ (Prompt-Aware Counting++), a novel test suite featuring two dedicated evaluation protocols – the negative-label test and the distractor test – paired with new specialized metrics; and (ii) we present the MUCCA (MUlti-Category Class-Agnostic counting) evaluation dataset, a new collection of real-world images featuring multiple annotated object categories per scene, unlike existing CAC benchmarks that typically include a single category per image. Our extensive experimental evaluation of 10 state-of-the-art methods shows that, despite strong performance under standard counting metrics, current models exhibit significant weaknesses in understanding and grounding object class descriptions. Finally, we provide a quantitative analysis of how semantic similarity between prompts influences these failures. Overall, our results underscore the need for more semantically grounded architectures and offer a reliable framework for future assessment in open-world text-guided CAC methods.
Read the full abstract

All authors Giacomo Pacini, Luca Ciampi, Nicola Messina, Nicola Tonellotto, Giuseppe Amato, Fabrizio Falchi

Computer Vision

Virtual Scanning for NSCLC Histology: Investigating the Discriminatory Power of Synthetic PET

Fatih Aksu, Laura Ciuffetti, Francesco Di Feola et al. (+6 more)

Accurate histological differentiation between adenocarcinoma (ADC) and squamous cell carcinoma (SCC) is critical for personalized treatment in non-small cell lung cancer (NSCLC). While [$^{18}$F]FDG PET/CT is a standard tool for the clinical evaluation of lung cancer, its utility is often limited by high costs and radiation exposure. In this paper, we investigate the feasibility of "virtual scanning" as a feature-enhancement strategy by evaluating whether synthetic PET data can provide complementary feature representations to supplement anatomical CT scans in histological subtype classification. We propose a framework that leverages a 3D Pix2Pix Generative Adversarial Network (GAN), pretrained on the FDG-PET/CT Lesions dataset, to synthesize pseudo-PET volumes from anatomical CT scans. These synthetic volumes are integrated with structural CT data within the MINT framework, a multi-stage intermediate fusion architecture. Our experiments, conducted on a multi-center dataset of 714 subjects, demonstrate that the inclusion of synthetic metabolic features significantly improves classification performance over a CT-only baseline. The multimodal approach achieved a statistically significant increase in the Area Under the Curve (AUC) from 0.489 to 0.591 and improved the Geometric Mean (GMean) from 0.305 to 0.524. These results suggest that synthetic PET scans provide discriminatory metabolic cues that enable deep learning models to exploit complementary cross-modal information, offering a potential feature-enhancement strategy for clinical scenarios where physical PET scans are unavailable.
Read the full abstract

All authors Fatih Aksu, Laura Ciuffetti, Francesco Di Feola, Filippo Ruffini, Giulia Romoli, Fabrizia Gelardi, Arturo Chiti, Valerio Guarrasi, Paolo Soda

Computer Vision · Cross-listed from cs.AI

Triple Spectral Fusion for Sensor-based Human Activity Recognition

Ye Zhang, Longguang Wang, Qing Gao et al. (+3 more)

The field of sensor-based human activity recognition (HAR) mainly uses posture, motion and context data of Inertial Measurement Units (IMUs) to identify daily activities. Despite the advancements in learning-based methods, it is challenging to perform information fusion from the temporal perspective due to the complexities in fusing heterogeneous sensor data and establishing long-term context correlations. This paper proposes a novel triple spectral fusion framework tailored for HAR. First, we develop an adaptive complementary filtering technique for noise suppression and organize each IMU's sensors into posture and motion modality nodes. Given that IMU nodes form a dynamic heterogeneous graph, we then apply adaptive filtering within the graph Fourier domain to merge both homogeneous and heterogeneous node information. Furthermore, an adaptive wavelet frequency selection approach is implemented to suppress context redundancy and shorten the length of features. This approach enhances both timestamp-based graph aggregation and the correlation of long-term contexts. Our framework uses adaptive filtering in the Fourier, graph Fourier, and wavelet domains, enabling effective multi-sensor fusion and context correlation. Extensive experiments on ten benchmark datasets demonstrate the superior performance of our framework. Project page: https://github.com/crocodilegogogo/TSF-TPAMI2026.
Read the full abstract

All authors Ye Zhang, Longguang Wang, Qing Gao, Chaocan Xiang, Mohammed Bennamoun, Yulan Guo

Computer Vision

SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training

Romain Valabregue, Ines Khemir, Eric Badinet et al. (+3 more)

Synthetic training has recently advanced brain MRI segmentation by enabling contrast-agnostic models trained entirely on generated data. However, most existing approaches rely on hundreds of automatically labeled templates, introducing systematic biases and limiting their flexibility to incorporate new anatomical structures. We present the Segment It All Model (SIAM), a 3D whole-head segmentation framework for 16 anatomical structures, trained using only six high-quality, manually annotated templates. SIAM extends domain randomization to both intensity and shape domains: synthetic image generation ensures contrast variability, while high-resolution spatial transformations model anatomical differences in cortical thickness and deep nuclei morphology. Unlike prior synthetic models, SIAM simultaneously segments brain as well as extra-cerebral tissues, including cerebrospinal fluid, vessels, dura mater, skull, and skin, enabling fully automated, preprocessing-free analysis. Evaluation across eight heterogeneous datasets (N=301), that include multiple contrasts (T1-weighted, T2-weighted, CT) and span a wide range of ages, demonstrates that SIAM matches or outperforms state-of-the-art methods for brain structures, in addition to extending automated segmentation to non-brain structures. The model also exhibits superior consistency across contrasts and repeated acquisitions, together with improved sensitivity to subtle gray matter atrophy. We openly release the model and the label templates at https://github.com/romainVala/SIAM.
Read the full abstract

All authors Romain Valabregue, Ines Khemir, Eric Badinet, François Rousseau, Guillaume Auzias, Reuben Dorent

Computer Vision

Perceptual Flow Network for Visually Grounded Reasoning

Yangfu Li, Yuning Gong, Hongjian Zhan et al. (+8 more)

Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias and hallucination. To mitigate this, current methods introduce geometric priors from visual experts as additional supervision. However, we observe that such supervision is typically suboptimal: it is biased toward geometric precision and offers limited reasoning utility. To bridge this gap, we propose Perceptual Flow Network (PFlowNet), which eschews rigid alignment with the expert priors and achieves interpretable yet more effective visual reasoning. Specifically, PFlowNet decouples perception from reasoning to establish a self-conditioned generation process. Based on this, it integrates multi-dimensional rewards with vicinal geometric shaping via variational reinforcement learning, thereby facilitating reasoning-oriented perceptual behaviors while preserving visual reliability. PFlowNet delivers a provable performance guarantee and competitive empirical results, particularly setting new SOTA records on V* Bench (90.6%) and MME-RealWorld-lite (67.0%).
Read the full abstract

All authors Yangfu Li, Yuning Gong, Hongjian Zhan, Teng Li, Yuanhuiyi Lyu, Tianyi Chen, Qi Liu, Ziyuan Huang, Zhihang Zhong, Dandan Zheng, Yue Lu

Computer Vision

Scientific Domain Knowledge Improves Vision-Language Fundus Models

Verena Jasmin Hallitschke, Carsten Eickhoff and Philipp Berens

Vision-language models hold considerable promise for ophthalmology, but it remains unclear which training data source best conveys expert domain knowledge. Existing ophthalmic models are trained on fixed text templates, medical reports, or general biomedical literature, sources that have never been compared under matched conditions. To include domain-specific literature in this comparison, we present PubMed-Ophtha, a hierarchical dataset with high domain density of 102,023 panels with their subcaptions from 15,842 open-access articles in PubMed Central. We then finetuned identical CLIP models on each source, using a general biomedical literature model as baseline, and found that domain-specific literature achieved the best average performance across 110 clinical tasks, reaching a mean linear probing AUROC of 88.63% ahead of medical reports (85.68%). Restricting the dataset to fundus images, to the image count of the medical report dataset, or to articles unrelated to the evaluation datasets did not reduce performance, indicating that the gains likely stem from domain density. We release the dataset, the finetuned models, and the full generation pipeline.
Read the full abstract

Computer Vision

OphMAE: Bridging Volumetric and Planar Imaging with a Foundation Model for Adaptive Ophthalmological Diagnosis

Tienyu Chang, Zhen Chen, Renjie Liang et al. (+9 more)

The advent of foundation models has heralded a new era in medical artificial intelligence (AI), enabling the extraction of generalizable representations from large-scale unlabeled datasets. However, current ophthalmic AI paradigms are predominantly constrained to single-modality inference, thereby creating a dissonance with clinical practice where diagnosis relies on the synthesis of complementary imaging modalities. Furthermore, the deployment of high-performance AI in resource-limited settings is frequently impeded by the unavailability of advanced three-dimensional imaging hardware. Here, we present the Ophthalmic multimodal Masked Autoencoder (OphMAE), a multi-imaging foundation model engineered to synergize the volumetric depth of 3D Optical Coherence Tomography (OCT) with the planar context of 2D en face OCT. By implementing a novel cross-modal fusion architecture and a unique adaptive inference mechanism, OphMAE was pre-trained on a massive dataset with of 183,875 paired OCT images derived from 32,765 patients. In a rigorous benchmark encompassing 17 diverse diagnostic tasks with 48,340 paired OCT images from 8,191 patients, the model demonstrated state-of-the-art performance, achieving an Area Under the Curve (AUC) of 96.9% for Age-related Macular Degeneration (AMD) and 97.2% for Diabetic Macular Edema (DME), consistently surpassing existing single-modal and multimodal foundation models. Crucially, OphMAE exhibits robust engineering adaptability: it maintains high diagnostic accuracy, such as 93.7% AUC for AMD, even when restricted to single-modality 2D inputs, and demonstrates exceptional data efficiency by retaining 95.7% AUC with as few as 500 labeled samples. This work establishes a scalable and adaptable framework for ophthalmic AI, ensuring robust performance across different tasks.
Read the full abstract

All authors Tienyu Chang, Zhen Chen, Renjie Liang, Jinyu Ding, Jie Xu, Sunu Mathew, Amir Reza Hajrasouliha, Andrew J. Saykin, Ruogu Fang, Yu Huang, Jiang Bian, Qingyu Chen

Computer Vision · Cross-listed from cs.RO

Temporally Consistent Object 6D Pose Estimation for Robot Control

Kateryna Zorina, Vojtech Priban, Mederic Fourmy et al. (+2 more)

Single-view RGB object pose estimators have reached a level of precision and efficiency that makes them good candidates for vision-based robot control. However, off-the-shelf methods lack temporal consistency and robustness that are mandatory for a stable feedback control. In this work, we develop a factor graph approach to enforce temporal consistency of the object pose estimates. In particular, the proposed approach: (i) incorporates object motion models, (ii) explicitly estimates the object pose measurement uncertainty, and (iii) integrates the above two components in an online optimization-based estimator. We demonstrate that with appropriate outlier rejection and smoothing using the proposed factor graph approach, we can significantly improve the results on standardized pose estimation benchmarks. We experimentally validate the stability of the proposed approach for a feedback-based robot control task in which the object is tracked by the camera attached to a torque controlled manipulator.
Read the full abstract

All authors Kateryna Zorina, Vojtech Priban, Mederic Fourmy, Josef Sivic, Vladimir Petrik

Computer Vision

SAIL: Structure-Aware Interpretable Learning for Anatomy-Aligned Post-hoc Explanations in OCT

Tienyu Chang, Tianhao Li, Ruogu Fang et al. (+2 more)

Optical coherence tomography (OCT), a commonly used retinal imaging modality, plays a central role in retinal disease diagnosis by providing high-resolution visualization of retinal layers. While deep learning (DL) has achieved expert-level accuracy in OCT-based retinal disease detection, its "black box" nature poses challenges for clinical adoption, where explainability is essential for clinical trust and regulatory approval. Existing post-hoc explainable AI (XAI) methods often struggle to delineate fine-grained lesion structures, respect anatomical boundaries, or suppress noise, limiting the trustworthiness of their explanations. To bridge these gaps, we propose a Structure-Aware Interpretable Learning (SAIL) framework that integrates retinal anatomical priors at the representation level and couples them with semantic features via a fusion design. Without modifying standard post-hoc explainability methods, this representation yields sharper and more anatomically aligned attribution maps. Comprehensive experiments on diverse OCT datasets demonstrate that our structure-aware method consistently enhances interpretability, producing clinically meaningful and anatomy-aware explanations. Ablation studies further show that strong interpretability requires both structural priors and semantic features, and that properly fusing the two is critical to achieve the best explanation quality. Together, these results highlight structure-aware representations as a key step toward reliable explainability in OCT.
Read the full abstract

All authors Tienyu Chang, Tianhao Li, Ruogu Fang, Jiang Bian, Yu Huang

Computer Vision · Cross-listed from cs.RO

Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions

Sergio Orozco, Tushar Kusnur, Brandon May et al. (+2 more)

Learning data-efficient object dynamics models for robotic manipulation remains challenging, especially for deformable objects. A popular approach is to model objects as sets of 3D particles and learn their motion using graph neural networks. In practice, this is not enough to maintain physical feasibility over long horizons and may require large amounts of interaction data to learn. We introduce PIEGraph, a novel approach to combining analytical physics and data-driven models to capture object dynamics for both rigid and deformable bodies using limited real-world interaction data. PIEGraph consists of two components: (1) a Physically Informed particle-based analytical model (implemented as a spring–mass system) to enforce physically feasible motion, and (2) an Equivariant Graph Neural Network with a novel action representation that exploits symmetries in particle interactions to guide the analytical model. We evaluate PIEGraph in simulation and on robot hardware for reorientation and repositioning tasks with ropes, cloth, stuffed animals and rigid objects. We show that our method enables accurate dynamics prediction and reliable downstream robotic manipulation planning, which outperforms state of the art baselines.
Read the full abstract

All authors Sergio Orozco, Tushar Kusnur, Brandon May, George Konidaris, Laura Herlant

Computer Vision · Cross-listed from cs.RO

AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs

Simon Dorer, Martin Büchner, Nick Heppert et al. (+1 more)

Dense and accurate depth estimation is essential for robotic manipulation, grasping, and navigation, yet currently available depth sensors are prone to errors on transparent, specular, and general non-Lambertian surfaces. To mitigate these errors, large-scale monocular depth estimation approaches provide strong structural priors, but their predictions can be potentially skewed or mis-scaled in metric units, limiting their direct use in robotics. Thus, in this work, we propose a training-free depth grounding framework that anchors monocular depth estimation priors from a depth foundation model in raw sensor depth through factor graph optimization. Our method performs a patch-wise affine alignment, locally grounding monocular predictions in metric real-world depth while preserving fine-grained geometric structure and discontinuities. To facilitate evaluation in challenging real-world conditions, we introduce a benchmark dataset with dense scene-wide ground truth depth in the presence of non-Lambertian objects. Ground truth is obtained via matte reflection spray and multi-camera fusion, overcoming the reliance on object-only CAD-based annotations used in prior datasets. Extensive evaluations across diverse sensors and domains demonstrate consistent improvements in depth performance without any (re-)training. We make our implementation publicly available at https://anchord.cs.uni-freiburg.de.
Read the full abstract

All authors Simon Dorer, Martin Büchner, Nick Heppert, Abhinav Valada

Computer Vision · Cross-listed from eess.IV

Biological Spatial Priors Regularize Foundation Model Representations for Cross-Site MSI Generalization in Colorectal Cancer

Dasari Naga Raju

Predicting microsatellite instability (MSI) status from routine hematoxylin and eosin (H&E) whole slide images (WSIs) offers a practical alternative to molecular testing, but models trained at one institution tend to generalize poorly to slides acquired at a different site. Foundation model representations, despite their generality, still encode site-specific texture alongside the conserved biological morphology underlying MSI. We investigate whether tile-level spatial priors derived from known MSI histology can guide these representations toward more site-invariant features. We introduce a biologically motivated spatial prior based on peripheral distance encoding, reflecting the Crohn's-like peripheral lymphocytic reaction at the tumor invasive margin, and evaluate a secondary local immune neighborhood encoding reflecting the lymphocyte-to-tumor ratio in each tile's immediate spatial neighborhood. Both priors are injected into a TransMIL aggregator before self-attention, allowing the transformer to integrate spatial biological context with UNI2-h or Virchow2 features across all attention layers. We evaluate six foundation model and MIL aggregator combinations as a reference, then assess the effect of each spatial prior. Training on TCGA-COAD (137 slides) and evaluating externally on TCGA-READ (50 slides) without retraining, peripheral distance encoding achieves MSI AUC 0.959 +/- 0.012 on COAD and MSS specificity 1.000 on READ, compared to 0.957 and 0.939 for the strongest reference configuration. Local immune neighborhood encoding achieves comparable internal AUC but lower cross-site specificity, suggesting margin proximity encodes a more site-invariant biological signal than local immune density. Results suggest biologically grounded spatial priors act as regularizers that reduce reliance on site-specific imaging patterns.
Read the full abstract

Computer Vision

Human Activity Recognition Method for Moderate Violence Detection

Luis Angel Aparicio Borjas, Victor Elias Nieto, Juan Irving Vasquez et al. (+2 more)

Physical violence in public spaces is a significant public health concern, with minor incidents such as pushing often serving as precursors to more severe escalations. This research develops an automated system for the real-time detection of moderate physical violence, specifically pushing, in surveillance camera footage. The proposed solution integrates state-of-the-art computer vision models, utilizing YOLO11 and YOLO11-Pose for human detection and skeletal keypoint extraction. By calculating body inclination and joint angles between shoulders and hips, a Random Forest classifier was trained to distinguish between normal behavior and aggressive physical contact. The system's performance was evaluated through three progressive case studies representing increasing levels of difficulty. In controlled environments with frontal views, the model achieved a precision of 0.98. In the most challenging scenario, featuring high-altitude, steep-angle recordings from real-world surveillance infrastructure, the system maintained a precision of 0.72 despite significant perspective distortion and visual noise. These results demonstrate the feasibility of using skeletal analysis for early violence intervention in urban security contexts.
Read the full abstract

All authors Luis Angel Aparicio Borjas, Victor Elias Nieto, Juan Irving Vasquez, Alfonso Fernandez-Vazquez, Gerardo Antonio Alvarez Hernandez

Computer Vision

Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE

Yangming Shi, Shixiang Zhu, Tao Shen et al. (+14 more)

We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the model's generation capability, we equip the Diffusion Transformer backbone with a fine-grained Mixture-of-Experts (MoE) design (128 experts, Top-8 routing), yielding a 25B-parameter model that activates only 3B parameters, significantly reducing training costs while scaling up the model capacity. Mamoda2.5 achieves top-tier generation performance on VBench 2.0 and sets a new record in video editing quality, surpassing evaluated open-source models and matching the performance of current top-tier proprietary models, including the Kling O1 on OpenVE-Bench. Furthermore, we introduce a joint few-step distillation and reinforcement learning framework that compresses the 30-step editing model into a 4-step model and greatly accelerates model inference. Compared to open-source baselines, Mamoda2.5 achieves up to $95.9\times$ faster video editing inference. In real-world applications, Mamoda2.5 has been successfully deployed for content moderation and creative restoration tasks in advertising scenarios, achieving a 98% success rate in internal advertising video editing scenario.
Read the full abstract

All authors Yangming Shi, Shixiang Zhu, Tao Shen, Zhimiao Yu, Dengsheng Chen, Taicai Chen, Yunfei Yang, Juan Zhou, Chen Cheng, Liang Ma, Xibin Wu, Benxuan Yan, Ge Li, Tuoyu Zhang, Dan Li, Chang Liu, Zhenbang Sun

Computer Vision

ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking

Jiawei Ge, Xintian Zhang, Jiuxin Cao et al. (+9 more)

Cross-view Referring Multi-Object Tracking (CRMOT) aims to track multiple objects specified by natural language across multiple camera views, with globally consistent identities. Despite recent progress, existing methods rely heavily on costly frame-level spatial annotations and cross-view identity supervision. To reduce such reliance, we explore CRMOT under weak supervision by leveraging the capabilities of foundation models. However, our empirical study shows that directly applying foundation models such as SAM2 and SAM3, even with task-specific modifications, fails to accurately understand referring expressions and maintain consistent identities across views. Yet, they remain effective at producing reliable object tracklets that can serve as pseudo supervision. We therefore repurpose foundation models as pseudo-label generators and propose a two-stage framework for weakly supervised CRMOT, using only object category labels as coarse-grained supervision. In the first stage, we design an Affinity-guided Cross-view Re-prompting strategy to refine and associate SAM3-generated tracklets across cameras, producing reliable cross-view pseudo labels for subsequent training. In the second stage, we introduce ViewSAM, a CRMOT model built upon SAM2 that explicitly models view-aware cross-modal semantics. By formulating view-induced variations as learnable conditions, ViewSAM bridges the gap between view-variant visual observations and view-invariant textual expressions, enabling robust cross-view referring tracking with only approximately 10% additional parameters. Extensive experiments demonstrate that ViewSAM achieves SOTA performance under weak supervision and remains competitive with fully supervised methods.
Read the full abstract

All authors Jiawei Ge, Xintian Zhang, Jiuxin Cao, Bo Liu, Fabian Deuser, Chang Liu, Gong Wenkang, Siyou Li, Juexi Shao, Wenqing Wu, Chen Feng, Ioannis Patras

Computer Vision

AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding

Ruilin Yao, Shegnwu Xiong, Tianyu Zou et al. (+2 more)

Vision-Language Models (VLMs) have enabled autonomous GUI agents that translate natural language instructions into executable screen coordinates. However, grounding performance degrades in high-resolution interfaces, where dense layouts and small interactive elements expose a resolution gap between modern displays and model input constraints. Existing zoom-in strategies rely on fixed anchors, heuristic grids, or reinforcement learning, lacking a principled mechanism to adaptively determine where refinement is needed and how much spatial uncertainty should be explored. We propose AutoFocus, a training-free, uncertainty-aware active visual search framework for GUI grounding. Our key insight is that token-level perplexity in coordinate generation naturally reflects spatial uncertainty. Rather than committing to a single prediction, AutoFocus samples multiple coordinate hypotheses and converts their axial perplexities into an anisotropic gaussian spatial probability field, explicitly modeling directional uncertainty. Based on this field, we generate global and local region proposals and introduce Shape-Aware Zooming to balance tight localization with contextual preservation. A visual prompt-based aggregation step then selects the most consistent prediction via structured comparison. Extensive experiments on ScreenSpot-Pro and ScreenSpot-V2 demonstrate consistent improvements across both general-purpose and GUI-specialized VLMs.
Read the full abstract

All authors Ruilin Yao, Shegnwu Xiong, Tianyu Zou, Shili Xiong, Yi Rong