Peer Revenue Returns subject to peer review

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision

Sunday 11 January

Computer Vision

Enhancing Low-resolution Image Representation Through Normalizing Flows

Chenglong Bao, Tongyao Pang, Zuowei Shen et al. (+2 more)

Low-resolution image representation can be regarded as a special form of sparse representation that retains only low-frequency information while discarding high-frequency components. This property reduces storage and transmission costs and benefits various image processing tasks. However, a key challenge is to preserve essential visual content while maintaining the ability to accurately reconstruct the original images. This work proposes LR2Flow, a nonlinear framework that learns low-resolution image representations by integrating wavelet tight frame blocks with normalizing flows. We conduct a reconstruction error analysis of the proposed network, which demonstrates the necessity of designing invertible neural networks in the wavelet tight frame domain. Experimental results on various tasks, including image rescaling, compression, and denoising, demonstrate the effectiveness of the learned representations and the robustness of the proposed framework. Code is available at https://github.com/Evanescentlove/LR2Flow-main.
Read the full abstract

All authors Chenglong Bao, Tongyao Pang, Zuowei Shen, Dihan Zheng, Yihang Zou

Computer Vision

SARA: Scene-Aware Reconstruction Accelerator

Jee Won Lee, Hansol Lim, Minhyeok Im et al. (+2 more)

We present SARA (Scene-Aware Reconstruction Accelerator), a geometry-driven pair selection module for Structure-from-Motion (SfM). Unlike conventional pipelines that select pairs based on visual similarity alone, SARA introduces geometry-first pair selection by scoring reconstruction informativeness - the product of overlap and parallax - before expensive matching. A lightweight pre-matching stage uses mutual nearest neighbors and RANSAC to estimate these cues, then constructs an Information-Weighted Spanning Tree (IWST) augmented with targeted edges for loop closure, long-baseline anchors, and weak-view reinforcement. Compared to exhaustive matching, SARA reduces rotation errors by 46.5+-5.5% and translation errors by 12.5+-6.5% across modern learned detectors, while achieving at most 50x speedup through 98% pair reduction (from 30,848 to 580 pairs). This reduces matching complexity from quadratic to quasi-linear, maintaining within +-3% of baseline reconstruction metrics for 3D Gaussian Splatting and SVRaster.
Read the full abstract

All authors Jee Won Lee, Hansol Lim, Minhyeok Im, Dohyeon Lee, Jongseong Brad Choi

Computer Vision

SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation

Jiwen Zhang, Zejun Li, Siyuan Wang et al. (+3 more)

Although learning-based vision-and-language navigation (VLN) agents can learn spatial knowledge implicitly from large-scale training data, zero-shot VLN agents lack this process, relying primarily on local observations for navigation, which leads to inefficient exploration and a significant performance gap. To deal with the problem, we consider a zero-shot VLN setting that agents are allowed to fully explore the environment before task execution. Then, we construct the Spatial Scene Graph (SSG) to explicitly capture global spatial structure and semantics in the explored environment. Based on the SSG, we introduce SpatialNav, a zero-shot VLN agent that integrates an agent-centric spatial map, a compass-aligned visual representation, and a remote object localization strategy for efficient navigation. Comprehensive experiments in both discrete and continuous environments demonstrate that SpatialNav significantly outperforms existing zero-shot agents and clearly narrows the gap with state-of-the-art learning-based methods. Such results highlight the importance of global spatial representations for generalizable navigation.
Read the full abstract

All authors Jiwen Zhang, Zejun Li, Siyuan Wang, Xiangyu Shi, Zhongyu Wei, Qi Wu

Computer Vision · Cross-listed from cs.CL

Forest Before Trees: Latent Superposition for Efficient Visual Reasoning

Yubo Wang, Juntian Zhang, Yichen Wu et al. (+3 more)

While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this challenge, but often fall prey to premature semantic collapse due to rigid autoregressive objectives. In this paper, we propose Laser, a novel paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning (DWAL). Instead of forcing a point-wise prediction, Laser aligns the latent state with a dynamic validity window of future semantics. This mechanism enforces a "Forest-before-Trees" cognitive hierarchy, enabling the model to maintain a probabilistic superposition of global features before narrowing down to local details. Crucially, Laser maintains interpretability via decodable trajectories while stabilizing unconstrained learning via Self-Refined Superposition. Extensive experiments on 6 benchmarks demonstrate that Laser achieves state-of-the-art performance among latent reasoning methods, surpassing the strong baseline Monet by 5.03% on average. Notably, it achieves these gains with extreme efficiency, reducing inference tokens by more than 97%, while demonstrating robust generalization to out-of-distribution domains.
Read the full abstract

All authors Yubo Wang, Juntian Zhang, Yichen Wu, Yankai Lin, Nils Lukas, Yuhan Liu

Computer Vision

CliffordNet: All You Need is Geometric Algebra

Zhongping Ji

Modern computer vision architectures, from CNNs to Transformers, predominantly rely on the stacking of heuristic modules: spatial mixers (Attention/Conv) followed by channel mixers (FFNs). In this work, we challenge this paradigm by returning to mathematical first principles. We propose the Clifford Algebra Network (CAN), also referred to as CliffordNet, a vision backbone grounded purely in Geometric Algebra. Instead of engineering separate modules for mixing and memory, we derive a unified interaction mechanism based on the Clifford Geometric Product ($uv = u \cdot v + u \wedge v$). This operation ensures algebraic completeness regarding the Geometric Product by simultaneously capturing feature coherence (via the generalized inner product) and structural variation (via the exterior wedge product). Implemented via an efficient sparse rolling mechanism with strict linear complexity $O(N)$, our model reveals a surprising emergent property: the geometric interaction is so representationally dense that standard Feed-Forward Networks (FFNs) become redundant. Empirically, CliffordNet establishes a new Pareto frontier: our Nano variant achieves 77.82% accuracy on CIFAR-100 with only 1.4M parameters, effectively matching the heavy-weight ResNet-18 (11.2M) with $8\times$ fewer parameters, while our Lite variant (2.6M) sets a new SOTA for tiny models at 79.05%. Our results suggest that global understanding can emerge solely from rigorous, algebraically complete local interactions, potentially signaling a shift where geometry is all you need. Code is available at https://github.com/ParaMind2025/CAN.
Read the full abstract

Computer Vision · Cross-listed from cs.HC

AutoTour: Automatic Photo Tour Guide with Smartphones and LLMs

Huatao Xu, Zihe Liu, Zilin Zeng et al. (+2 more)

We present AutoTour, a system that enhances user exploration by automatically generating fine-grained landmark annotations and descriptive narratives for photos captured by users. The key idea of AutoTour is to fuse visual features extracted from photos with nearby geospatial features queried from open matching databases. Unlike existing tour applications that rely on pre-defined content or proprietary datasets, AutoTour leverages open and extensible data sources to provide scalable and context-aware photo-based guidance. To achieve this, we design a training-free pipeline that first extracts and filters relevant geospatial features around the user's GPS location. It then detects major landmarks in user photos through VLM-based feature detection and projects them into the horizontal spatial plane. A geometric matching algorithm aligns photo features with corresponding geospatial entities based on their estimated distance and direction. The matched features are subsequently grounded and annotated directly on the original photo, accompanied by large language model-generated textual and audio descriptions to provide an informative, tour-like experience. We demonstrate that AutoTour can deliver rich, interpretable annotations for both iconic and lesser-known landmarks, enabling a new form of interactive, context-aware exploration that bridges visual perception and geospatial understanding.
Read the full abstract

All authors Huatao Xu, Zihe Liu, Zilin Zeng, Baichuan Li, Mo Li

Computer Vision

The Normalized Difference Layer: A Differentiable Spectral Index Formulation for Deep Learning

Ali Lotfi, Adam Carter, Mohammad Meysami et al. (+3 more)

Normalized difference indices have been a staple in remote sensing for decades. They stay reliable under lighting changes produce bounded values and connect well to biophysical signals. Even so, they are usually treated as a fixed pre processing step with coefficients set to one, which limits how well they can adapt to a specific learning task. In this study, we introduce the Normalized Difference Layer that is a differentiable neural network module. The proposed method keeps the classical idea but learns the band coefficients from data. We present a complete mathematical framework for integrating this layer into deep learning architectures that uses softplus reparameterization to ensure positive coefficients and bounded denominators. We describe forward and backward pass algorithms enabling end to end training through backpropagation. This approach preserves the key benefits of normalized differences, namely illumination invariance and outputs bounded to $[-1,1]$ while allowing gradient descent to discover task specific band weightings. We extend the method to work with signed inputs, so the layer can be stacked inside larger architectures. Experiments show that models using this layer reach similar classification accuracy to standard multilayer perceptrons while using about 75% fewer parameters. They also handle multiplicative noise well, at 10% noise accuracy drops only 0.17% versus 3.03% for baseline MLPs. The learned coefficient patterns stay consistent across different depths.
Read the full abstract

All authors Ali Lotfi, Adam Carter, Mohammad Meysami, Thuan Ha, Kwabena Nketia, Steve Shirtliffe

Computer Vision

Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models

Shaonan Liu, Guo Yu, Xiaoling Luo et al. (+4 more)

Medical Multimodal Large Language Models (Med-MLLMs) require egocentric clinical intent understanding for real-world deployment, yet existing benchmarks fail to evaluate this critical capability. To address these challenges, we introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation. Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical workflows, and implicit adherence to safety protocols. We propose a Three-Dimensional Clinical Intent Framework evaluating: (1) Spatial Intent: discriminating precise targets amid visual noise, (2) Temporal Intent: inferring causal rationale through retrospective and prospective reasoning, and (3) Standard Intent: verifying protocol compliance through safety checks. Beyond accuracy metrics, we introduce Trap QA mechanisms to stress-test clinical reliability by penalizing hallucinations and cognitive sycophancy. Experiments reveal current MLLMs struggle with egocentric intent due to over-reliance on global features, leading to fabricated observations and uncritical acceptance of invalid instructions.
Read the full abstract

All authors Shaonan Liu, Guo Yu, Xiaoling Luo, Shiyi Zheng, Wenting Chen, Jie Liu, Linlin Shen

Computer Vision · Cross-listed from eess.IV

USFetal: Tools for Fetal Brain Ultrasound Compounding

Mohammad Khateri, Morteza Ghahremani, Sergio Valencia et al. (+5 more)

Ultrasound offers a safe, cost-effective, and widely accessible technology for fetal brain imaging, making it especially suitable for routine clinical use. However, it suffers from view-dependent artifacts, operator variability, and a limited field of view, which make interpretation and quantitative evaluation challenging. Ultrasound compounding aims to overcome these limitations by integrating complementary information from multiple 3D acquisitions into a single, coherent volumetric representation. This work provides four main contributions: (1) We present the first systematic categorization of computational strategies for fetal brain ultrasound compounding, including both classical techniques and modern learning-based frameworks. (2) We implement and compare representative methods across four key categories - multi-scale, transformation-based, variational, and deep learning approaches - emphasizing their core principles and practical advantages. (3) Motivated by the lack of full-view, artifact-free ground truth required for supervised learning, we focus on unsupervised and self-supervised strategies and introduce two new deep learning based approaches: a self-supervised compounding framework and an adaptation of unsupervised deep plug-and-play priors for compounding. (4) We conduct a comprehensive evaluation on ten multi-view fetal brain ultrasound datasets, using both expert radiologist scoring and standard quantitative image-quality metrics. We also release the USFetal Compounding Toolbox, publicly available to support benchmarking and future research. Keywords: Ultrasound compounding, fetal brain, deep learning, self-supervised, unsupervised.
Read the full abstract

All authors Mohammad Khateri, Morteza Ghahremani, Sergio Valencia, Camilo Jaimes, Alejandra Sierra, Jussi Tohka, P. Ellen Grant, Davood Karimi

Computer Vision

When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge

Mahsa Mitcheff and Adam Czajka

Iris recognition is a mature biometric technology offering remarkable precision and speed, and allowing for large-scale deployments to populations exceeding a billion enrolled users (e.g., AADHAAR in India). However, in forensic applications, a human expert may be needed to review and confirm a positive identification before an iris matching result can be presented as evidence in court, especially in cases where processed samples are degraded (e.g., in post-mortem cases) or where there is a need to judge whether the sample is authentic, rather than a result of a presentation attack. This paper presents a study that examines human performance in iris verification in two controlled scenarios: (a) under varying pupil sizes, with and without a linear/nonlinear alignment of the pupil size between compared images, and (b) when both genuine and impostor iris image pairs are synthetically generated. The results demonstrate that pupil size normalization carried out by a modern autoencoder-based identity-preserving image-to-image translation model significantly improves verification accuracy. Participants were also able to determine whether iris pairs corresponded to the same or different eyes when both images were either authentic or synthetic. However, accuracy declined when subjects were comparing authentic irises against high-quality, same-eye synthetic counterparts. These findings (a) demonstrate the importance of pupil-size alignment for iris matching tasks in which humans are involved, and (b) indicate that despite the high fidelity of modern generative models, same-eye synthetic iris images are more often judged by humans as different-eye images, compared to same-eye authentic image pairs. We offer data and human judgments along with this paper to allow full replicability of this study and future works.
Read the full abstract

Saturday 10 January

Computer Vision

PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAM

Xu Wang, Boyao Han, Xiaojun Chen et al. (+2 more)

Real-time 3D reconstruction is crucial for robotics and augmented reality, yet current simultaneous localization and mapping(SLAM) approaches often struggle to maintain structural consistency and robust pose estimation in the presence of depth noise. This work introduces PointSLAM++, a novel RGB-D SLAM system that leverages a hierarchically constrained neural Gaussian representation to preserve structural relationships while generating Gaussian primitives for scene mapping. It also employs progressive pose optimization to mitigate depth sensor noise, significantly enhancing localization accuracy. Furthermore, it utilizes a dynamic neural representation graph that adjusts the distribution of Gaussian nodes based on local geometric complexity, enabling the map to adapt to intricate scene details in real time. This combination yields high-precision 3D mapping and photorealistic scene rendering. Experimental results show PointSLAM++ outperforms existing 3DGS-based SLAM methods in reconstruction accuracy and rendering quality, demonstrating its advantages for large-scale AR and robotics.
Read the full abstract

All authors Xu Wang, Boyao Han, Xiaojun Chen, Ying Liu, Ruihui Li

Computer Vision · Cross-listed from cs.NE

Line-based Event Preprocessing: Towards Low-Energy Neuromorphic Computer Vision

Amélie Gruel, Pierre Lewden, Adrien F. Vincent et al. (+1 more)

Neuromorphic vision made significant progress in recent years, thanks to the natural match between spiking neural networks and event data in terms of biological inspiration, energy savings, latency and memory use for dynamic visual data processing. However, optimising its energy requirements still remains a challenge within the community, especially for embedded applications. One solution may reside in preprocessing events to optimise data quantity thus lowering the energy cost on neuromorphic hardware, proportional to the number of synaptic operations. To this end, we extend an end-to-end neuromorphic line detection mechanism to introduce line-based event data preprocessing. Our results demonstrate on three benchmark event-based datasets that preprocessing leads to an advantageous trade-off between energy consumption and classification performance. Depending on the line-based preprocessing strategy and the complexity of the classification task, we show that one can maintain or increase the classification accuracy while significantly reducing the theoretical energy consumption. Our approach systematically leads to a significant improvement of the neuromorphic classification efficiency, thus laying the groundwork towards a more frugal neuromorphic computer vision thanks to event preprocessing.
Read the full abstract

All authors Amélie Gruel, Pierre Lewden, Adrien F. Vincent, Sylvain Saïghi

2601.10742 · 10 Jan · 18 pages (3 pages of acknowledgments and references), 10 figures and 4 tables. Submitted to the IOP Science "Neuromorphic Computing and Engineering" journal, awaiting feedback. This work is supported by a public grant overseen by the French National Research Agency (ANR) as part of the éPEPR IA France 2030é programme (Emergences project ANR-23-PEIA-0002)

Abstract PDF $VISN ×3$BNCH ×1$DATA ×1$MEM ×1

Computer Vision · Cross-listed from q-bio.QM

Imaging-anchored multiomics in cardiovascular disease: integrating cardiac imaging, bulk, single-cell, and spatial transcriptomics

Minh H. N. Le, Thanh-Huy Nguyen, Tao Li et al. (+7 more)

Cardiovascular disease arises from interactions between inherited risk, molecular programmes, and tissue-scale remodelling that are observed clinically through imaging. Cardiac MRI (CMR), computed tomography (CT), and echocardiography are integral to routine cardiovascular care, while bulk RNA sequencing, single-cell RNA sequencing, and spatial transcriptomics are providing increasingly detailed molecular characterization of cardiac tissue. Yet, these imaging and molecular data are still analysed in largely separate pipelines. This review examines joint representations that link cardiac imaging phenotypes to transcriptomic and spatially resolved molecular states. An imaging-anchored perspective is adopted in which echocardiography, CMR, and CT define a spatial phenotype of the heart, and bulk, single-cell and spatial transcriptomics provide cell-type- and location-specific molecular context. We define the representation requirements of each modality, compare multimodal fusion strategies, and synthesize integrative pipelines for radiogenomics, spatial alignment, and image-based gene-expression prediction, together with their validation requirements, limitations, and failure modes. Spatial multiomic maps of human myocardium and atherosclerotic plaque, together with single-cell, spatial, and multimodal medical foundation models, are advancing imaging-anchored multiomics; however, cost, scalability, and tissue availability remain substantial barriers to large-scale cardiovascular translation.
Read the full abstract

All authors Minh H. N. Le, Thanh-Huy Nguyen, Tao Li, Bao Quang Gia Le, Han H. Huynh, Monika Raj, Carl Yang, Min Xu, Tuan Vinh, Nguyen Quoc Khanh Le

Computer Vision · Cross-listed from cs.LG

HOSC: A Periodic Activation with Saturation Control for High-Fidelity Implicit Neural Representations

Michal Jan Wlodarczyk, Danzel Serrano and Przemyslaw Musialski

Periodic activations such as sine preserve high-frequency information in implicit neural representations (INRs) through their oscillatory structure, but often suffer from gradient instability and limited control over multi-scale behavior. We introduce the Hyperbolic Oscillator with Saturation Control (HOSC) activation, $\text{HOSC}(x) = \tanh\bigl(\beta \sin(\omega_0 x)\bigr)$, which exposes an explicit parameter $\beta$ that controls the Lipschitz bound of the activation by $\beta \omega_0$. This provides a direct mechanism to tune gradient magnitudes while retaining a periodic carrier. We provide a mathematical analysis and conduct a comprehensive empirical study across images, audio, video, NeRFs, and SDFs using standardized training protocols. Comparative analysis against SIREN, FINER, and related methods shows where HOSC provides substantial benefits and where it achieves competitive parity. Results establish HOSC as a practical periodic activation for INR applications, with domain-specific guidance on hyperparameter selection. For code visit the project page https://hosc-nn.github.io/ .
Read the full abstract

Computer Vision · Cross-listed from cs.LG

Beyond Perfect Scores: Proof-by-Contradiction for Trustworthy Machine Learning

Dushan N. Wadduwage, Dineth Jayakody and Leonidas Zimianitis

Machine learning (ML) models show strong promise for new biomedical prediction tasks, but concerns about trustworthiness have hindered their clinical adoption. In particular, it is often unclear whether a model relies on true clinical cues or on spurious hierarchical correlations in the data. This paper introduces a simple yet broadly applicable trustworthiness test grounded in stochastic proof-by-contradiction. Instead of just showing high test performance, our approach trains and tests on spurious labels carefully permuted based on a potential outcomes framework. A truly trustworthy model should fail under such label permutation; comparable accuracy across real and permuted labels indicates overfitting, shortcut learning, or data leakage. Our approach quantifies this behavior through interpretable Fisher-style p-values, which are well understood by domain experts across medical and life sciences. We evaluate our approach on multiple new bacterial diagnostics to separate tasks and models learning genuine causal relationships from those driven by dataset artifacts or statistical coincidences. Our work establishes a foundation to build rigor and trust between ML and life-science research communities, moving ML models one step closer to clinical adoption.
Read the full abstract

Computer Vision

Quantification and Classification of Carbon Nanotubes in Electron Micrographs using Vision Foundation Models

Sanjay Pradeep, Chen Wang, Matthew M. Dahm et al. (+2 more)

Accurate characterization of carbon nanotube morphologies in electron microscopy images is vital for exposure assessment and toxicological studies, yet current workflows rely on slow, subjective manual segmentation. This work presents a unified framework leveraging vision foundation models to automate the quantification and classification of CNTs in electron microscopy images. First, we introduce an interactive quantification tool built on the Segment Anything Model (SAM) that segments particles with near-perfect accuracy using minimal user input. Second, we propose a novel classification pipeline that utilizes these segmentation masks to spatially constrain a DINOv2 vision transformer, extracting features exclusively from particle regions while suppressing background noise. Evaluated on a dataset of 1,800 TEM images, this architecture achieves 95.5% accuracy in distinguishing between four different CNT morphologies, significantly outperforming the current baseline despite using a fraction of the training data. Crucially, this instance-level processing allows the framework to resolve mixed samples, correctly classifying distinct particle types co-existing within a single field of view. These results demonstrate that integrating zero-shot segmentation with self-supervised feature learning enables high-throughput, reproducible nanomaterial analysis, transforming a labor-intensive bottleneck into a scalable, data-driven process.
Read the full abstract

All authors Sanjay Pradeep, Chen Wang, Matthew M. Dahm, Jeff D. Eldredge, Candace S.J. Tsai

Computer Vision

eSkiTB: A Synthetic Event-based Dataset for Tracking Skiers

Krishna Vinod, Joseph Raj Vishal, Kaustav Chanda et al. (+3 more)

Tracking skiers in RGB broadcast footage is challenging due to motion blur, static overlays, and clutter that obscure the fast-moving athlete. Event cameras, with their asynchronous contrast sensing, offer natural robustness to such artifacts, yet a controlled benchmark for winter-sport tracking has been missing. We introduce event SkiTB (eSkiTB), a synthetic event-based ski tracking dataset generated from SkiTB using direct video-to-event conversion without neural interpolation, enabling an iso-informational comparison between RGB and event modalities. Benchmarking SDTrack (spiking transformer) against STARK (RGB transformer), we find that event-based tracking is substantially resilient to broadcast clutter in scenes dominated by static overlays, achieving 0.685 IoU, outperforming RGB by +20.0 points. Across the dataset, SDTrack attains a mean IoU of 0.711, demonstrating that temporal contrast is a reliable cue for tracking ballistic motion in visually congested environments. eSkiTB establishes the first controlled setting for event-based tracking in winter sports and highlights the promise of event cameras for ski tracking. The dataset and code will be released at https://github.com/eventbasedvision/eSkiTB.
Read the full abstract

All authors Krishna Vinod, Joseph Raj Vishal, Kaustav Chanda, Prithvi Jai Ramesh, Yezhou Yang, Bharatesh Chakravarthi

Computer Vision

Boosting Overlapping Organoid Instance Segmentation Using Pseudo-Label Unmixing and Synthesis-Assisted Learning

Gui Huang, Kangyuan Zheng, Xuan Cai et al. (+7 more)

Organoids, sophisticated in vitro models of human tissues, are crucial for medical research due to their ability to simulate organ functions and assess drug responses accurately. Accurate organoid instance segmentation is critical for quantifying their dynamic behaviors, yet remains profoundly limited by high-quality annotated datasets and pervasive overlap in microscopy imaging. While semi-supervised learning (SSL) offers a solution to alleviate reliance on scarce labeled data, conventional SSL frameworks suffer from biases induced by noisy pseudo-labels, particularly in overlapping regions. Synthesis-assisted SSL (SA-SSL) has been proposed for mitigating training biases in semi-supervised semantic segmentation. We present the first adaptation of SA-SSL to organoid instance segmentation and reveal that SA-SSL struggles to disentangle intertwined organoids, often misrepresenting overlapping instances as a single entity. To overcome this, we propose Pseudo-Label Unmixing (PLU), which identifies erroneous pseudo-labels for overlapping instances and then regenerates organoid labels through instance decomposition. For image synthesis, we apply a contour-based approach to synthesize organoid instances efficiently, particularly for overlapping cases. Instance-level augmentations (IA) on pseudo-labels before image synthesis further enhances the effect of synthetic data (SD). Rigorous experiments on two organoid datasets demonstrate our method's effectiveness, achieving performance comparable to fully supervised models using only 10% labeled data, and state-of-the-art results. Ablation studies validate the contributions of PLU, contour-based synthesis, and augmentation-aware training. By addressing overlap at both pseudo-label and synthesis levels, our work advances scalable, label-efficient organoid analysis, unlocking new potential for high-throughput applications in precision medicine.
Read the full abstract

All authors Gui Huang, Kangyuan Zheng, Xuan Cai, Jiaqi Wang, Jianjia Zhang, Kaida Ning, Wenbo Wei, Yujuan Zhu, Jiong Zhang, Mengting Liu

Computer Vision

Sissi: Zero-shot Style-guided Image Synthesis via Semantic-style Integration

Yingying Deng, Xiangyu He, Fan Tang et al. (+2 more)

Text-guided image generation has advanced rapidly with large-scale diffusion models, yet achieving precise stylization with visual exemplars remains difficult. Existing approaches often depend on task-specific retraining or expensive inversion procedures, which can compromise content integrity, reduce style fidelity, and lead to an unsatisfactory trade-off between semantic prompt adherence and style alignment. In this work, we introduce a training-free framework that reformulates style-guided synthesis as an in-context learning task. Guided by textual semantic prompts, our method concatenates a reference style image with a masked target image, leveraging a pretrained ReFlow-based inpainting model to seamlessly integrate semantic content with the desired style through multimodal attention fusion. We further analyze the imbalance and noise sensitivity inherent in multimodal attention fusion and propose a Dynamic Semantic-Style Integration (DSSI) mechanism that reweights attention between textual semantic and style visual tokens, effectively resolving guidance conflicts and enhancing output coherence. Experiments show that our approach achieves high-fidelity stylization with superior semantic-style balance and visual quality, offering a simple yet powerful alternative to complex, artifact-prone prior methods.
Read the full abstract

All authors Yingying Deng, Xiangyu He, Fan Tang, Weiming Dong, Xucheng Yin

Computer Vision

APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation

Dongliang Chen, Xinlin Zhuang, Junjie Xu et al. (+8 more)

Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance, high-responsiveness objectives (e.g., OCR) while under-optimizing perceptual goals. We identify two mechanistic causes: variance hijacking, where reward dispersion induces implicit reweighting that dominates the normalized training signal, and gradient conflicts, where competing objectives produce opposing update directions and trigger seesaw-like oscillations. We propose APEX (Adaptive Priority-based Efficient X-objective Alignment), which stabilizes heterogeneous rewards with Dual-Stage Adaptive Normalization and dynamically schedules objectives via P^3 Adaptive Priorities that combine learning potential, conflict penalty, and progress need. On Stable Diffusion 3.5, APEX achieves improved Pareto trade-offs across four heterogeneous objectives, with balanced gains of +1.31 PickScore, +0.35 DeQA, and +0.53 Aesthetics while maintaining competitive OCR accuracy, mitigating the instability of multi-objective alignment.
Read the full abstract

All authors Dongliang Chen, Xinlin Zhuang, Junjie Xu, Luojian Xie, Zehui Wang, Jiaxi Zhuang, Haolin Yang, Liang Dou, Xiao He, Xingjiao Wu, Ying Qian

Computer Vision

QCaption: Video Captioning and Q&A through Fusion of Large Multimodal Models

Jiale Wang, Gee Wah Ng, Lee Onn Mak et al. (+3 more)

This paper introduces QCaption, a novel video captioning and Q&A pipeline that enhances video analytics by fusing three models: key frame extraction, a Large Multimodal Model (LMM) for image-text analysis, and a Large Language Model (LLM) for text analysis. This approach enables integrated analysis of text, images, and video, achieving performance improvements over existing video captioning and Q&A models; all while remaining fully self-contained, adept for on-premises deployment. Experimental results using QCaption demonstrated up to 44.2% and 48.9% improvements in video captioning and Q&A tasks, respectively. Ablation studies were also performed to assess the role of LLM on the fusion on the results. Moreover, the paper proposes and evaluates additional video captioning approaches, benchmarking them against QCaption and existing methodologies. QCaption demonstrate the potential of adopting a model fusion approach in advancing video analytics.
Read the full abstract

All authors Jiale Wang, Gee Wah Ng, Lee Onn Mak, Randall Cher, Ng Ding Hei Ryan, Davis Wang

Computer Vision

ArrowGEV: Grounding Events in Video via Learning the Arrow of Time

Fangxu Yu, Ziyao Lu, Liqiang Niu et al. (+2 more)

Grounding events in videos serves as a fundamental capability in video analysis. While Vision Language Models (VLMs) are increasingly employed for this task, existing approaches predominantly train models to associate events with timestamps in the forward video only. This paradigm hinders VLMs from capturing the inherent temporal structure and directionality of events, thereby limiting robustness and generalization. To address this limitation, inspired by the arrow of time in physics, which characterizes the intrinsic directionality of temporal processes, we propose ArrowGEV, a reinforcement learning framework that explicitly models temporal directionality in events to improve both event grounding and temporal directionality understanding in VLMs. Specifically, we categorize events into time-sensitive (e.g., putting down a bag) and time-insensitive (e.g., holding a towel in the left hand). The former denote events whose reversal substantially alters their meaning, while the latter remain semantically unchanged under reversal. For time-sensitive events, ArrowGEV introduces a reward that encourages VLMs to discriminate between forward and backward videos, whereas for time-insensitive events, it enforces consistent grounding across both directions. Extensive experiments demonstrate that ArrowGEV not only improves grounding precision and temporal directionality recognition, but also enhances general video understanding and reasoning ability.
Read the full abstract

All authors Fangxu Yu, Ziyao Lu, Liqiang Niu, Fandong Meng, Jie Zhou

Computer Vision · Cross-listed from cs.IT

Robust Sparse Signal Recovery with Outliers: A Hard Thresholding Pursuit Approach Based on LAD

Jiao Xu, Peng Li and Bing Zheng

Recovering a sparse signal from outlier-contaminated measurements is a fundamental challenge in many applications. While existing algorithms predominantly address scenarios with bounded noise or assume known signal sparsity, few methods tackle the more practical problem of sparse recovery from gross outliers without prior knowledge of sparsity. To bridge this gap, we study the sparsity-constrained Least Absolute Deviations (LAD) minimization problem. This paper proposes the Graded Fast Hard Thresholding Pursuit (GFHTP$_1$) algorithm with a quantile-truncated step size for $\ell_1$-loss minimization. In contrast to most state-of-the-art methods, our GFHTP$_1$ requires no prior knowledge of the signal's sparsity level. We establish a theoretical convergence analysis under mild conditions and further prove that an $s$-sparse signal can be recovered exactly within at most $s$ iterations. To our knowledge, these results provide the first efficient recovery guarantees for sparse signal reconstruction from outlier-corrupted measurements without a sparsity prior. Numerical experiments demonstrate that GFHTP$_1$ consistently outperforms competing algorithms in robustness to varying signal sparsity and outlier support size, while also achieving less computational time.
Read the full abstract

Computer Vision

Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework

Pan Liao, Feng Yang, Di Wu et al. (+3 more)

Semantic Multi-Object Tracking (SMOT) is evolving from purely geometric localization toward comprehensive video understanding. However, existing paradigms predominantly rely on closed-set interaction tags and fragmented perception pipelines, creating a bottleneck that prevents the full utilization of Multi-modal Large Language Models (MLLMs) for dynamic scenes. In this paper, we elevate SMOT from rigid classification to an open-ended generative reasoning task. To support this paradigm shift, we introduce Grand-SMOT, a large-scale benchmark featuring high-density, dual-stream narratives. This dataset explicitly decouples micro-level individual dynamics from macro-level environmental contexts, directly resolving the semantic scarcity of prior tracking datasets. Furthermore, we propose LLMTrack, a unified MLLM-driven framework for dynamic SMOT. Guided by a verifiable “Macro-Understanding-First” mechanism, LLMTrack employs a Spatio-Temporal Fusion Module to compress discrete geometric trajectories into continuous semantic tokens, effectively suppressing temporal hallucinations in long-sequence tracking. Extensive experiments, utilizing a novel decoupled evaluation protocol, validate that LLMTrack achieves state-of-the-art geometric tracking robustness while delivering a qualitative leap in generative semantic reasoning. The code and datasets are publicly available at https://github.com/liaopan-lp/LLMTrack-GrandSMOT.
Read the full abstract

All authors Pan Liao, Feng Yang, Di Wu, Jinwen Yu, Wang Zhao, Dingwen Zhang

Computer Vision

Towards Egocentric 3D Hand Pose Estimation in Unseen Domains

Wiktor Mucha, Michael Wray and Martin Kampel

We present V-HPOT, a novel approach for improving the cross-domain performance of 3D hand pose estimation from egocentric images across diverse, unseen domains. State-of-the-art methods demonstrate strong performance when trained and tested within the same domain. However, they struggle to generalise to new environments due to limited training data and depth perception – overfitting to specific camera intrinsics. Our method addresses this by estimating keypoint z-coordinates in a virtual camera space, normalised by focal length and image size, enabling camera-agnostic depth prediction. We further leverage this invariance to camera intrinsics to propose a self-supervised test-time optimisation strategy that refines the model's depth perception during inference. This is achieved by applying a 3D consistency loss between predicted and in-space scale-transformed hand poses, allowing the model to adapt to target domain characteristics without requiring ground truth annotations. V-HPOT significantly improves 3D hand pose estimation performance in cross-domain scenarios, achieving a 71% reduction in mean pose error on the H2O dataset and a 41% reduction on the AssemblyHands dataset. Compared to state-of-the-art methods, V-HPOT outperforms all single-stage approaches across all datasets and competes closely with two-stage methods, despite needing approximately x3.5 to x14 less data.
Read the full abstract

Computer Vision

Toward Generalizable Deblurring: Leveraging Massive Blur Priors with Linear Attention for Real-World Scenarios

Yuanting Gao, Shuo Cao, Xiaohui Li et al. (+3 more)

Image deblurring has advanced rapidly with deep learning, yet most methods exhibit poor generalization beyond their training datasets, with performance dropping significantly in real-world scenarios. Our analysis shows this limitation stems from two factors: datasets face an inherent trade-off between realism and coverage of diverse blur patterns, and algorithmic designs remain restrictive, as pixel-wise losses drive models toward local detail recovery while overlooking structural and semantic consistency, whereas diffusion-based approaches, though perceptually strong, still fail to generalize when trained on narrow datasets with simplistic strategies. Through systematic investigation, we identify blur pattern diversity as the decisive factor for robust generalization and propose Blur Pattern Pretraining (BPP), which acquires blur priors from simulation datasets and transfers them through joint fine-tuning on real data. We further introduce Motion and Semantic Guidance (MoSeG) to strengthen blur priors under severe degradation, and integrate it into GLOWDeblur, a Generalizable reaL-wOrld lightWeight Deblur model that combines convolution-based pre-reconstruction & domain alignment module with a lightweight diffusion backbone. Extensive experiments on six widely-used benchmarks and two real-world datasets validate our approach, confirming the importance of blur priors for robust generalization and demonstrating that the lightweight design of GLOWDeblur ensures practicality in real-world applications. The project page is available at https://vegdog007.github.io/GLOWDeblur_Website/.
Read the full abstract

All authors Yuanting Gao, Shuo Cao, Xiaohui Li, Yuandong Pu, Yihao Liu, Kai Zhang

Computer Vision

BabyVision: Visual Reasoning Beyond Language

Liang Chen, Weichu Xie, Yiyan Liang et al. (+27 more)

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.
Read the full abstract

All authors Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Hans Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang Shen, Xuanzhong Chen, Wendong Xu, Shuzheng Si, Zefan Cai, Wenhao Chai, Ziqi Huang, Fangfu Liu, Tianyu Liu, Baobao Chang, Ming Wu, Xiaobo Hu, Kaiyuan Chen, Yixin Ren, Yang Liu, Yuan Gong, Kuan Li

Computer Vision

Bridging Robustness and Efficiency: Real-Time Low-Light Enhancement via Attention U-Net GAN

Yash Thesia and Meera Suthar

Recent advancements in Low-Light Image Enhancement (LLIE) have focused heavily on Diffusion Probabilistic Models, which achieve high perceptual quality but suffer from significant computational latency (often exceeding 2-4 seconds per image). Conversely, traditional CNN-based baselines offer real-time inference but struggle with "over-smoothing," failing to recover fine structural details in extreme low-light conditions. This creates a practical gap in the literature: the lack of a model that provides generative-level texture recovery at edge-deployable speeds. In this paper, we address this trade-off by proposing a hybrid Attention U-Net GAN. We demonstrate that the heavy iterative sampling of diffusion models is not strictly necessary for texture recovery. Instead, by integrating Attention Gates into a lightweight U-Net backbone and training within a conditional adversarial framework, we can approximate the high-frequency fidelity of generative models in a single forward pass. Extensive experiments on the SID dataset show that our method achieves a best-in-class LPIPS score of 0.112 among efficient models, significantly outperforming efficient baselines (SID, EnlightenGAN) while maintaining an inference latency of 0.06s. This represents a 40x speedup over latent diffusion models, making our approach suitable for near real-time applications.
Read the full abstract

Computer Vision · Cross-listed from cs.RO

Precision Meets Art: Autonomous Multi-UAV System for Large Scale Mural Drawing

Andrei A. Korigodskii, Artem E. Vasiunik, Georgii A. Varin et al. (+5 more)

The integration of autonomous unmanned aerial vehicles (UAVs) into large-scale artistic projects has emerged as a new application in robotics. This paper presents the design, deployment, and testing of a novel multi-drone system for automated mural painting in outdoor settings. This technology makes use of new software that coordinates multiple drones simultaneously, utilizing state-machine algorithms for task execution. Key advancements are the complex positioning system that combines 2D localization using a single motion tracking camera with onboard LiDAR for precise positioning, and a novel flight control algorithm, which works differently along the trajectory and normally to it, ensuring smoothness and high precision of the drawings at the same time. A 100 square meters mural was created using the developed multi-drone system, validating the system's efficacy. Compared to single-drone approaches, our multi-UAV solution significantly improves scalability and operational speed while maintaining high stability even in harsh weather conditions. The findings highlight the potential of autonomous robotic swarms in creative applications, paving the way for further advancements in large-scale robotic art.
Read the full abstract

All authors Andrei A. Korigodskii, Artem E. Vasiunik, Georgii A. Varin, Adilia M. Zukhurova, Matvei V. Urvantsev, Semen A. Osipenkov, Igor S. Efremov, Georgii E. Bondar

Computer Vision

3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence

Hao Tang, Ting Huang and Zeyu Zhang

Spatial intelligence refers to the ability to perceive, reason about, and describe objects and their relationships within three-dimensional environments, forming a foundation for embodied perception and scene understanding. 3D captioning aims to describe 3D scenes in natural language; however, it remains challenging due to the sparsity and irregularity of point clouds and, more critically, the weak grounding and limited out-of-distribution (OOD) generalization of existing captioners across drastically different environments, including indoor and outdoor 3D scenes. To address this challenge, we propose 3D CoCa v2, a generalizable 3D captioning framework that unifies contrastive vision-language learning with 3D caption generation and further improves robustness via test-time search (TTS) without updating the captioner parameters. 3D CoCa v2 builds on a frozen CLIP-based semantic prior, a spatially-aware 3D scene encoder for geometry, and a multimodal decoder jointly optimized with contrastive and captioning objectives, avoiding external detectors or handcrafted proposals. At inference, TTS produces diverse caption candidates and performs reward-guided selection using a compact scene summary. Experiments show improvements over 3D CoCa of +1.50 CIDEr@0.5IoU on ScanRefer and +1.61 CIDEr@0.5IoU on Nr3D, and +3.8 CIDEr@0.25 in zero-shot OOD evaluation on TOD3Cap. Code will be released at https://github.com/AIGeeksGroup/3DCoCav2.
Read the full abstract