Peer Revenue Play credits. Real papers.

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision (sign in to use)

Monday 10 November

Computer Vision

YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting

Fast and flexible 3D scene reconstruction from unstructured image collections remains a significant challenge. We present YoNoSplat, a feedforward model that reconstructs high-quality 3D Gaussian Splatting representations from an arbitrary number of images. Our model is highly versatile, operating effectively with both posed and unposed, calibrated and uncalibrated inputs. YoNoSplat predicts local Gaussians and camera poses for each view, which are aggregated into a global representation using either predicted or provided poses. To overcome the inherent difficulty of jointly learning 3D Gaussians and camera parameters, we introduce a novel mixing training strategy. This approach mitigates the entanglement between the two tasks by initially using ground-truth poses to aggregate local Gaussians and gradually transitioning to a mix of predicted and ground-truth poses, which prevents both training instability and exposure bias. We further resolve the scale ambiguity problem by a novel pairwise camera-distance normalization scheme and by embedding camera intrinsics into the network. Moreover, YoNoSplat also predicts intrinsic parameters, making it feasible for uncalibrated inputs. YoNoSplat demonstrates exceptional efficiency, reconstructing a scene from 100 views (at 280x518 resolution) in just 2.69 seconds on an NVIDIA GH200 GPU. It achieves state-of-the-art performance on standard benchmarks in both pose-free and pose-dependent settings. Our project page is at https://botaoye.github.io/yonosplat/.
Read the full abstract

All authors Botao Ye, Boqi Chen, Haofei Xu, Daniel Barath, Marc Pollefeys

Computer Vision

Beyond Boundaries: Leveraging Vision Foundation Models for Source-Free Object Detection

Source-Free Object Detection (SFOD) aims to adapt a source-pretrained object detector to a target domain without access to source data. However, existing SFOD methods predominantly rely on internal knowledge from the source model, which limits their capacity to generalize across domains and often results in biased pseudo-labels, thereby hindering both transferability and discriminability. In contrast, Vision Foundation Models (VFMs), pretrained on massive and diverse data, exhibit strong perception capabilities and broad generalization, yet their potential remains largely untapped in the SFOD setting. In this paper, we propose a novel SFOD framework that leverages VFMs as external knowledge sources to jointly enhance feature alignment and label quality. Specifically, we design three VFM-based modules: (1) Patch-weighted Global Feature Alignment (PGFA) distills global features from VFMs using patch-similarity-based weighting to enhance global feature transferability; (2) Prototype-based Instance Feature Alignment (PIFA) performs instance-level contrastive learning guided by momentum-updated VFM prototypes; and (3) Dual-source Enhanced Pseudo-label Fusion (DEPF) fuses predictions from detection VFMs and teacher models via an entropy-aware strategy to yield more reliable supervision. Extensive experiments on six benchmarks demonstrate that our method achieves state-of-the-art SFOD performance, validating the effectiveness of integrating VFMs to simultaneously improve transferability and discriminability.
Read the full abstract

All authors Huizai Yao, Sicheng Zhao, Pengteng Li, Yi Cui, Shuo Lu, Weiyu Guo, Yunfan Lu, Yijie Xu, Hui Xiong

Computer Vision

VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models

Video anomaly understanding (VAU) aims to provide detailed interpretation and semantic comprehension of anomalous events within videos, addressing limitations of traditional methods that focus solely on detecting and localizing anomalies. However, existing approaches often neglect the deeper causal relationships and interactions between objects, which are critical for understanding anomalous behaviors. In this paper, we propose VADER, an LLM-driven framework for Video Anomaly unDErstanding, which integrates keyframe object Relation features with visual cues to enhance anomaly comprehension from video. Specifically, VADER first applies an Anomaly Scorer to assign per-frame anomaly scores, followed by a Context-AwarE Sampling (CAES) strategy to capture the causal context of each anomalous event. A Relation Feature Extractor and a COntrastive Relation Encoder (CORE) jointly model dynamic object interactions, producing compact relational representations for downstream reasoning. These visual and relational cues are integrated with LLMs to generate detailed, causally grounded descriptions and support robust anomaly-related question answering. Experiments on multiple real-world VAU benchmarks demonstrate that VADER achieves strong results across anomaly description, explanation, and causal reasoning tasks, advancing the frontier of explainable video anomaly analysis.
Read the full abstract

All authors Ying Cheng, Yu-Ho Lin, Min-Hung Chen, Fu-En Yang, Shang-Hong Lai

Computer Vision

LMM-IQA: Image Quality Assessment for Low-Dose CT Imaging

Low-dose computed tomography (CT) represents a significant improvement in patient safety through lower radiation doses, but increased noise, blur, and contrast loss can diminish diagnostic quality. Therefore, consistency and robustness in image quality assessment become essential for clinical applications. In this study, we propose an LLM-based quality assessment system that generates both numerical scores and textual descriptions of degradations such as noise, blur, and contrast loss. Furthermore, various inference strategies - from the zero-shot approach to metadata integration and error feedback - are systematically examined, demonstrating the progressive contribution of each method to overall performance. The resultant assessments yield not only highly correlated scores but also interpretable output, thereby adding value to clinical workflows. The source codes of our study are available at https://github.com/itu-biai/lmms_ldct_iqa.
Read the full abstract

All authors Kagan Celik, Mehmet Ozan Unal, Metin Ertas, Isa Yildirim

Computer Vision · Cross-listed from cs.LO

Formal Reasoning About Confidence and Automated Verification of Neural Networks

In the last decade, a large body of work has emerged on robustness of neural networks, i.e., checking if the decision remains unchanged when the input is slightly perturbed. However, most of these approaches ignore the confidence of a neural network on its output. In this work, we aim to develop a generalized framework for formally reasoning about the confidence along with robustness in neural networks. We propose a simple yet expressive grammar that captures various confidence-based specifications. We develop a novel and unified technique to verify all instances of the grammar in a homogeneous way, viz., by adding a few additional layers to the neural network, which enables the use any state-of-the-art neural network verification tool. We perform an extensive experimental evaluation over a large suite of 8870 benchmarks, where the largest network has 138M parameters, and show that this outperforms ad-hoc encoding approaches by a significant margin.
Read the full abstract

All authors Mohammad Afzal, S. Akshay, Blaise Genest, Ashutosh Gupta

Computer Vision · Cross-listed from cs.RO

PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Driving

Most recent work in autonomous driving has prioritized benchmark performance and methodological innovation over in-depth analysis of model failures, biases, and shortcut learning. This has led to incremental improvements without a deep understanding of the current failures. While it is straightforward to look at situations where the model fails, it is hard to understand the underlying reason. This motivates us to conduct a systematic study, where inputs to the model are perturbed and the predictions observed. We introduce PlanT 2.0, a lightweight, object-centric planning transformer designed for autonomous driving research in CARLA. The object-level representation enables controlled analysis, as the input can be easily perturbed (e.g., by changing the location or adding or removing certain objects), in contrast to sensor-based models. To tackle the scenarios newly introduced by the challenging CARLA Leaderboard 2.0, we introduce multiple upgrades to PlanT, achieving state-of-the-art performance on Longest6 v2, Bench2Drive, and the CARLA validation routes. Our analysis exposes insightful failures, such as a lack of scene understanding caused by low obstacle diversity, rigid expert behaviors leading to exploitable shortcuts, and overfitting to a fixed set of expert trajectories. Based on these findings, we argue for a shift toward data-centric development, with a focus on richer, more robust, and less biased datasets. We open-source our code and model at https://github.com/autonomousvision/plant2.
Read the full abstract

Computer Vision · Cross-listed from eess.IV

CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video

The prevalence of user-generated content (UGC) on platforms such as YouTube and TikTok has rendered no-reference (NR) perceptual video quality assessment (VQA) vital for optimizing video delivery. Nonetheless, the characteristics of non-professional acquisition and the subsequent transcoding of UGC video on sharing platforms present significant challenges for NR-VQA. Although NR-VQA models attempt to infer mean opinion scores (MOS), their modeling of subjective scores for compressed content remains limited due to the absence of fine-grained perceptual annotations of artifact types. To address these challenges, we propose CAMP-VQA, a novel NR-VQA framework that exploits the semantic understanding capabilities of large vision-language models. Our approach introduces a quality-aware prompting mechanism that integrates video metadata (e.g., resolution, frame rate, bitrate) with key fragments extracted from inter-frame variations to guide the BLIP-2 pretraining approach in generating fine-grained quality captions. A unified architecture has been designed to model perceptual quality across three dimensions: semantic alignment, temporal characteristics, and spatial characteristics. These multimodal features are extracted and fused, then regressed to video quality scores. Extensive experiments on a wide variety of UGC datasets demonstrate that our model consistently outperforms existing NR-VQA methods, achieving improved accuracy without the need for costly manual fine-grained annotations. Our method achieves the best performance in terms of average rank and linear correlation (SRCC: 0.928, PLCC: 0.938) compared to state-of-the-art methods. The source code and trained models, along with a user-friendly demo, are available at: https://github.com/xinyiW915/CAMP-VQA.
Read the full abstract

All authors Xinyi Wang, Angeliki Katsenou, Junxiao Shen, David Bull

Computer Vision

Glioma C6: A Novel Dataset for Training and Benchmarking Cell Segmentation

We present Glioma C6, a new open dataset for instance segmentation of glioma C6 cells, designed as both a benchmark and a training resource for deep learning models. The dataset comprises 75 high-resolution phase-contrast microscopy images with over 12,000 annotated cells, providing a realistic testbed for biomedical image analysis. It includes soma annotations and morphological cell categorization provided by biologists. Additional categorization of cells, based on morphology, aims to enhance the utilization of image data for cancer cell research. Glioma C6 consists of two parts: the first is curated with controlled parameters for benchmarking, while the second supports generalization testing under varying conditions. We evaluate the performance of several generalist segmentation models, highlighting their limitations on our dataset. Our experiments demonstrate that training on Glioma C6 significantly enhances segmentation performance, reinforcing its value for developing robust and generalizable models. The dataset is publicly available for researchers.
Read the full abstract

All authors Roman Malashin, Svetlana Pashkevich, Daniil Ilyukhin, Arseniy Volkov, Valeria Yachnaya, Andrey Denisov, Maria Mikhalkova

Computer Vision

Segmentation of Ischemic Stroke Lesions using Transfer Learning on Multi-sequence MRI

The accurate understanding of ischemic stroke lesions is critical for efficient therapy and prognosis of stroke patients. Magnetic resonance imaging (MRI) is sensitive to acute ischemic stroke and is a common diagnostic method for stroke. However, manual lesion segmentation performed by experts is tedious, time-consuming, and prone to observer inconsistency. Automatic medical image analysis methods have been proposed to overcome this challenge. However, previous approaches have relied on hand-crafted features that may not capture the irregular and physiologically complex shapes of ischemic stroke lesions. In this study, we present a novel framework for quickly and automatically segmenting ischemic stroke lesions on various MRI sequences, including T1-weighted, T2-weighted, DWI, and FLAIR. The proposed methodology is validated on the ISLES 2015 Brain Stroke sequence dataset, where we trained our model using the Res-Unet architecture twice: first, with pre-existing weights, and then without, to explore the benefits of transfer learning. Evaluation metrics, including the Dice score and sensitivity, were computed across 3D volumes. Finally, a Majority Voting Classifier was integrated to amalgamate the outcomes from each axis, resulting in a comprehensive segmentation method. Our efforts culminated in achieving a Dice score of 80.5% and an accuracy of 74.03%, showcasing the efficacy of our segmentation approach.
Read the full abstract

Computer Vision

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression

Video Large Language Models (Video-LLMs) have demonstrated significant potential in the areas of video captioning, search, and summarization. However, current Video-LLMs still face challenges with long real-world videos. Recent methods have introduced a retrieval mechanism that retrieves query-relevant KV caches for question answering, enhancing the efficiency and accuracy of long real-world videos. However, the compression and retrieval of KV caches are still not fully explored. In this paper, we propose StreamKV, a training-free framework that seamlessly equips Video-LLMs with advanced KV cache retrieval and compression. Compared to previous methods that used uniform partitioning, StreamKV dynamically partitions video streams into semantic segments, which better preserves semantic information. For KV cache retrieval, StreamKV calculates a summary vector for each segment to retain segment-level information essential for retrieval. For KV cache compression, StreamKV introduces a guidance prompt designed to capture the key semantic elements within each segment, ensuring only the most informative KV caches are retained for answering questions. Moreover, StreamKV unifies KV cache retrieval and compression within a single module, performing both in a layer-adaptive manner, thereby further improving the effectiveness of streaming video question answering. Extensive experiments on public StreamingVQA benchmarks demonstrate that StreamKV significantly outperforms existing Online Video-LLMs, achieving superior accuracy while substantially improving both memory efficiency and computational latency. The code has been released at https://github.com/sou1p0wer/StreamKV.
Read the full abstract

All authors Yilong Chen, Xiang Bai, Zhibin Wang, Chengyu Bai, Yuhan Dai, Ming Lu, Shanghang Zhang

Computer Vision · Cross-listed from eess.AS

Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models

Large language models (LLMs) have recently achieved impressive results in speech recognition across multiple modalities, including Auditory Speech Recognition (ASR), Visual Speech Recognition (VSR), and Audio-Visual Speech Recognition (AVSR). Despite this progress, current LLM-based approaches typically address each task independently, training separate models that raise computational and deployment resource use while missing potential cross-task synergies. They also rely on fixed-rate token compression, which restricts flexibility in balancing accuracy with efficiency. These limitations highlight the need for a unified framework that can support ASR, VSR, and AVSR while enabling elastic inference. To this end, we present Omni-AVSR, a unified audio-visual LLM that combines efficient multi-granularity training with parameter-efficient adaptation. Specifically, we adapt the matryoshka representation learning paradigm to efficiently train across multiple audio and visual granularities, reducing its inherent training resource use. Furthermore, we explore three LoRA-based strategies for adapting the backbone LLM, balancing shared and task-specific specialization. Experiments on LRS2 and LRS3 show that Omni-AVSR achieves comparable or superior accuracy to state-of-the-art baselines while training a single model at substantially lower training and deployment resource use. The model also remains robust under acoustic noise, and we analyze its scaling behavior as LLM size increases, providing insights into the trade-off between performance and efficiency.
Read the full abstract

All authors Umberto Cappellazzo, Xubo Liu, Pingchuan Ma, Stavros Petridis, Maja Pantic

Computer Vision

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

The advent of Multimodal Large Language Models (MLLMs) has expanded AI capabilities to visual modalities, yet existing evaluation benchmarks remain limited to single-video understanding, overlooking the critical need for multi-video understanding in real-world scenarios (e.g., sports analytics and autonomous driving). To address this significant gap, we introduce MVU-Eval, the first comprehensive benchmark for evaluating Multi-Video Understanding for MLLMs. Specifically, our MVU-Eval mainly assesses eight core competencies through 1,824 meticulously curated question-answer pairs spanning 4,959 videos from diverse domains, addressing both fundamental perception tasks and high-order reasoning tasks. These capabilities are rigorously aligned with real-world applications such as multi-sensor synthesis in autonomous systems and cross-angle sports analytics. Through extensive evaluation of state-of-the-art open-source and closed-source models, we reveal significant performance discrepancies and limitations in current MLLMs' ability to perform understanding across multiple videos. The benchmark will be made publicly available to foster future research.
Read the full abstract

All authors Tianhao Peng, Haochen Wang, Yuanxing Zhang, Zekun Wang, Zili Wang, Gavin Chang, Jian Yang, Shihao Li, Yanghai Wang, Xintao Wang, Houyi Li, Wei Ji, Pengfei Wan, Steven Huang, Zhaoxiang Zhang, Jiaheng Liu

Computer Vision

4DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generation

Remarkable advances in recent 2D image and 3D shape generation have induced a significant focus on dynamic 4D content generation. However, previous 4D generation methods commonly struggle to maintain spatial-temporal consistency and adapt poorly to rapid temporal variations, due to the lack of effective spatial-temporal modeling. To address these problems, we propose a novel 4D generation network called 4DSTR, which modulates generative 4D Gaussian Splatting with spatial-temporal rectification. Specifically, temporal correlation across generated 4D sequences is designed to rectify deformable scales and rotations and guarantee temporal consistency. Furthermore, an adaptive spatial densification and pruning strategy is proposed to address significant temporal variations by dynamically adding or deleting Gaussian points with the awareness of their pre-frame movements. Extensive experiments demonstrate that our 4DSTR achieves state-of-the-art performance in video-to-4D generation, excelling in reconstruction quality, spatial-temporal consistency, and adaptation to rapid temporal movements.
Read the full abstract

All authors Mengmeng Liu, Jiuming Liu, Yunpeng Zhang, Jiangtao Li, Michael Ying Yang, Francesco Nex, Hao Cheng

Computer Vision

Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation

In autonomous driving and robotics, ensuring road safety and reliable decision-making critically depends on out-of-distribution (OOD) segmentation. While numerous methods have been proposed to detect anomalous objects on the road, leveraging the vision-language space-which provides rich linguistic knowledge-remains an underexplored field. We hypothesize that incorporating these linguistic cues can be especially beneficial in the complex contexts found in real-world autonomous driving scenarios. To this end, we present a novel approach that trains a Text-Driven OOD Segmentation model to learn a semantically diverse set of objects in the vision-language space. Concretely, our approach combines a vision-language model's encoder with a transformer decoder, employs Distance-Based OOD prompts located at varying semantic distances from in-distribution (ID) classes, and utilizes OOD Semantic Augmentation for OOD representations. By aligning visual and textual information, our approach effectively generalizes to unseen objects and provides robust OOD segmentation in diverse driving environments. We conduct extensive experiments on publicly available OOD segmentation datasets such as Fishyscapes, Segment-Me-If-You-Can, and Road Anomaly datasets, demonstrating that our approach achieves state-of-the-art performance across both pixel-level and object-level evaluations. This result underscores the potential of vision-language-based OOD segmentation to bolster the safety and reliability of future autonomous driving systems.
Read the full abstract

Computer Vision

Noise & pattern: identity-anchored Tikhonov regularization for robust structural anomaly detection

Anomaly detection plays a pivotal role in automated industrial inspection, aiming to identify subtle or rare defects in otherwise uniform visual patterns. As collecting representative examples of all possible anomalies is infeasible, we tackle structural anomaly detection using a self-supervised autoencoder that learns to repair corrupted inputs. To this end, we introduce a corruption model that injects artificial disruptions into training images to mimic structural defects. While reminiscent of denoising autoencoders, our approach differs in two key aspects. First, instead of unstructured i.i.d.\ noise, we apply structured, spatially coherent perturbations that make the task a hybrid of segmentation and inpainting. Second, and counterintuitively, we add and preserve Gaussian noise on top of the occlusions, which acts as a Tikhonov regularizer anchoring the Jacobian of the reconstruction function toward identity. This identity-anchored regularization stabilizes reconstruction and further improves both detection and segmentation accuracy. On the MVTec AD benchmark, our method achieves state-of-the-art results (I/P-AUROC: 99.9/99.4), supporting our theoretical framework and demonstrating its practical relevance for automatic inspection.
Read the full abstract

Computer Vision

Semi-supervised Shelter Mapping for WASH Accessibility Assessment in Rohingya Refugee Camps

Lack of access to Water, Sanitation, and Hygiene (WASH) services is a major public health concern in refugee camps, where extreme crowding accelerates the spread of communicable diseases. The Rohingya settlements in Cox's Bazar, Bangladesh, exemplify these conditions, with large populations living under severe spatial constraints. We develop a semi-supervised segmentation framework using the Segment Anything Model (SAM) to map shelters from multi-temporal sub-meter remote sensing imagery (2017-2025), improving detection in complex camp environments by 4.9% in F1-score over strong baselines. The detected shelter maps show that shelter expansion stabilized after 2020, whereas continued population growth reduced per capita living space by approximately 14% between 2020 and 2025. WASH accessibility, measured with an enhanced network-based two-step floating catchment area (2SFCA) method, declined from 2022 to 2025, increasing facility loads and exceeding global benchmarks. Gender-disaggregated scenarios that incorporate safety penalty further reveal pronounced inequities, with female accessibility approximately 27% lower than male. Together, these results demonstrate that remote sensing-driven AI diagnostics can generate equity-focused evidence to prioritize WASH investments and mitigate health risks in protracted displacement settings.
Read the full abstract

All authors Kyeongjin Ahn, YongHun Suh, Sungwon Han, Jeasurk Yang, Hannes Taubenböck, Meeyoung Cha

Computer Vision

Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images

This paper presents Omni-View, which extends the unified multimodal understanding and generation to 3D scenes based on multiview images, exploring the principle that "generation facilitates understanding". Consisting of understanding model, texture module, and geometry module, Omni-View jointly models scene understanding, novel view synthesis, and geometry estimation, enabling synergistic interaction between 3D scene understanding and generation tasks. By design, it leverages the spatiotemporal modeling capabilities of its texture module responsible for appearance synthesis, alongside the explicit geometric constraints provided by its dedicated geometry module, thereby enriching the model's holistic understanding of 3D scenes. Trained with a two-stage strategy, Omni-View achieves a state-of-the-art score of 55.4 on the VSI-Bench benchmark, outperforming existing specialized 3D understanding models, while simultaneously delivering strong performance in both novel view synthesis and 3D scene generation. The code and pretraiend models are open-sourced at https://github.com/AIDC-AI/Omni-View.
Read the full abstract

All authors JiaKui Hu, Shanshan Zhao, Qing-Guo Chen, Xuerui Qiu, Jialun Liu, Zhao Xu, Weihua Luo, Kaifu Zhang, Yanye Lu

Computer Vision

Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization

Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison rate required for a successful attack induces a proportional, and thus noticeable, drop in Clean Accuracy (CA), undermining their stealthiness. This paper presents a new paradigm for clean-image attacks that minimizes this accuracy degradation by optimizing the trigger itself. We introduce Generative Clean-Image Backdoors (GCB), a framework that uses a conditional InfoGAN to identify naturally occurring image features that can serve as potent and stealthy triggers. By ensuring these triggers are easily separable from benign task-related features, GCB enables a victim model to learn the backdoor from an extremely small set of poisoned examples, resulting in a CA drop of less than 1%. Our experiments demonstrate GCB's remarkable versatility, successfully adapting to six datasets, five architectures, and four tasks, including the first demonstration of clean-image backdoors in regression and segmentation. GCB also exhibits resilience against most of the existing backdoor defenses.
Read the full abstract

All authors Binyan Xu, Fan Yang, Di Tang, Xilin Dai, Kehuan Zhang

Computer Vision

Geometric implicit neural representations for signed distance functions

Implicit neural representations (INRs) have emerged as a promising framework for representing signals in low-dimensional spaces. This survey reviews the existing literature on the specialized INR problem of approximating signed distance functions (SDFs) for surface scenes, using either oriented point clouds or a set of posed images. We refer to neural SDFs that incorporate differential geometry tools, such as normals and curvatures, in their loss functions as geometric INRs. The key idea behind this 3D reconstruction approach is to include additional regularization terms in the loss function, ensuring that the INR satisfies certain global properties that the function should hold – such as having unit gradient in the case of SDFs. We explore key methodological components, including the definition of INR, the construction of geometric loss functions, and sampling schemes from a differential geometry perspective. Our review highlights the significant advancements enabled by geometric INRs in surface reconstruction from oriented point clouds and posed images.
Read the full abstract

All authors Luiz Schirmer, Tiago Novello, Vinícius da Silva, Guilherme Schardong, Daniel Perazzo, Hélio Lopes, Nuno Gonçalves, Luiz Velho

Computer Vision

Automated Estimation of Anatomical Risk Metrics for Endoscopic Sinus Surgery Using Deep Learning

Endoscopic sinus surgery requires careful preoperative assessment of the skull base anatomy to minimize risks such as cerebrospinal fluid leakage. Anatomical risk scores like the Keros, Gera and Thailand-Malaysia-Singapore score offer a standardized approach but require time-consuming manual measurements on coronal CT or CBCT scans. We propose an automated deep learning pipeline that estimates these risk scores by localizing key anatomical landmarks via heatmap regression. We compare a direct approach to a specialized global-to-local learning strategy and find mean absolute errors on the relevant anatomical measurements of 0.506mm for the Keros, 4.516{\deg} for the Gera and 0.802mm / 0.777mm for the TMS classification.
Read the full abstract

All authors Konrad Reuter, Lennart Thaysen, Bilkay Doruk, Sarah Latus, Brigitte Holst, Benjamin Becker, Dennis Eggert, Christian Betz, Anna-Sophie Hoffmann, Alexander Schlaefer

Computer Vision

LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors

The rapid progress of generative AI has led to the emergence of new generative models, while existing detection methods struggle to keep pace, resulting in significant degradation in the detection performance. This highlights the urgent need for continuously updating AI-generated image detectors to adapt to new generators. To overcome low efficiency and catastrophic forgetting in detector updates, we propose LiteUpdate, a lightweight framework for updating AI-generated image detectors. LiteUpdate employs a representative sample selection module that leverages image confidence and gradient-based discriminative features to precisely select boundary samples. This approach improves learning and detection accuracy on new distributions with limited generated images, significantly enhancing detector update efficiency. Additionally, LiteUpdate incorporates a model merging module that fuses weights from multiple fine-tuning trajectories, including pre-trained, representative, and random updates. This balances the adaptability to new generators and mitigates the catastrophic forgetting of prior knowledge. Experiments demonstrate that LiteUpdate substantially boosts detection performance in various detectors. Specifically, on AIDE, the average detection accuracy on Midjourney improved from 87.63% to 93.03%, a 6.16% relative increase.
Read the full abstract

All authors Jiajie Lu, Zhenkan Fu, Na Zhao, Long Xing, Kejiang Chen, Weiming Zhang, Nenghai Yu

Computer Vision

Federated Learning for Video Violence Detection: Complementary Roles of Lightweight CNNs and Vision-Language Models for Energy-Efficient Use

Deep learning-based video surveillance increasingly demands privacy-preserving architectures with low computational and environmental overhead. Federated learning preserves privacy but deploying large vision-language models (VLMs) introduces major energy and sustainability challenges. We compare three strategies for federated violence detection under realistic non-IID splits on the RWF-2000 and RLVS datasets: zero-shot inference with pretrained VLMs, LoRA-based fine-tuning of LLaVA-NeXT-Video-7B, and personalized federated learning of a 65.8M-parameter 3D CNN. All methods exceed 90% accuracy in binary violence detection. The 3D CNN achieves superior calibration (ROC AUC 92.59%) at roughly half the energy cost (240 Wh vs. 570 Wh) of federated LoRA, while VLMs provide richer multimodal reasoning. Hierarchical category grouping (based on semantic similarity and class exclusion) boosts VLM multiclass accuracy from 65.31% to 81% on the UCF-Crime dataset. To our knowledge, this is the first comparative simulation study of LoRA-tuned VLMs and personalized CNNs for federated violence detection, with explicit energy and CO2e quantification. Our results inform hybrid deployment strategies that default to efficient CNNs for routine inference and selectively engage VLMs for complex contextual reasoning.
Read the full abstract

Computer Vision

ProcGen3D: Learning Neural Procedural Graph Representations for Image-to-3D Reconstruction

We introduce ProcGen3D, a new approach for 3D content creation by generating procedural graph abstractions of 3D objects, which can then be decoded into rich, complex 3D assets. Inspired by the prevalent use of procedural generators in production 3D applications, we propose a sequentialized, graph-based procedural graph representation for 3D assets. We use this to learn to approximate the landscape of a procedural generator for image-based 3D reconstruction. We employ edge-based tokenization to encode the procedural graphs, and train a transformer prior to predict the next token conditioned on an input RGB image. Crucially, to enable better alignment of our generated outputs to an input image, we incorporate Monte Carlo Tree Search (MCTS) guided sampling into our generation process, steering output procedural graphs towards more image-faithful reconstructions. Our approach is applicable across a variety of objects that can be synthesized with procedural generators. Extensive experiments on cacti, trees, and bridges show that our neural procedural graph generation outperforms both state-of-the-art generative 3D methods and domain-specific modeling techniques. Furthermore, this enables improved generalization on real-world input images, despite training only on synthetic data.
Read the full abstract

All authors Xinyi Zhang, Daoyi Gao, Naiqi Li, Angela Dai

Computer Vision

MPJudge: Towards Perceptual Assessment of Music-Induced Paintings

Music induced painting is a unique artistic practice, where visual artworks are created under the influence of music. Evaluating whether a painting faithfully reflects the music that inspired it poses a challenging perceptual assessment task. Existing methods primarily rely on emotion recognition models to assess the similarity between music and painting, but such models introduce considerable noise and overlook broader perceptual cues beyond emotion. To address these limitations, we propose a novel framework for music induced painting assessment that directly models perceptual coherence between music and visual art. We introduce MPD, the first large scale dataset of music painting pairs annotated by domain experts based on perceptual coherence. To better handle ambiguous cases, we further collect pairwise preference annotations. Building on this dataset, we present MPJudge, a model that integrates music features into a visual encoder via a modulation based fusion mechanism. To effectively learn from ambiguous cases, we adopt Direct Preference Optimization for training. Extensive experiments demonstrate that our method outperforms existing approaches. Qualitative results further show that our model more accurately identifies music relevant regions in paintings.
Read the full abstract

All authors Shiqi Jiang, Tianyi Liang, Huayuan Ye, Changbo Wang, Chenhui Li

Computer Vision

Sparse4DGS: 4D Gaussian Splatting for Sparse-Frame Dynamic Scene Reconstruction

Dynamic Gaussian Splatting approaches have achieved remarkable performance for 4D scene reconstruction. However, these approaches rely on dense-frame video sequences for photorealistic reconstruction. In real-world scenarios, due to equipment constraints, sometimes only sparse frames are accessible. In this paper, we propose Sparse4DGS, the first method for sparse-frame dynamic scene reconstruction. We observe that dynamic reconstruction methods fail in both canonical and deformed spaces under sparse-frame settings, especially in areas with high texture richness. Sparse4DGS tackles this challenge by focusing on texture-rich areas. For the deformation network, we propose Texture-Aware Deformation Regularization, which introduces a texture-based depth alignment loss to regulate Gaussian deformation. For the canonical Gaussian field, we introduce Texture-Aware Canonical Optimization, which incorporates texture-based noise into the gradient descent process of canonical Gaussians. Extensive experiments show that when taking sparse frames as inputs, our method outperforms existing dynamic or few-shot techniques on NeRF-Synthetic, HyperNeRF, NeRF-DS, and our iPhone-4D datasets.
Read the full abstract

All authors Changyue Shi, Chuxiao Yang, Xinyuan Hu, Minghao Chen, Wenwen Pan, Yan Yang, Jiajun Ding, Zhou Yu, Jun Yu

Computer Vision

HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Driving

Three-dimensional feature extraction and multi-task perception are fundamental components of modern autonomous driving systems. Although large image encoders, high-resolution inputs, and long temporal contexts can substantially improve representation quality and overall performance, jointly leveraging these strategies remains challenging due to prohibitive computational costs during both training and inference. Furthermore, different perception tasks often require distinct feature representations, making it difficult for a unified architecture to achieve end-to-end multi-task performance comparable to specialized single-task systems. To address these challenges, we propose HENet++, a unified framework for multi-task 3D perception and end-to-end autonomous driving that employs a hybrid image encoding strategy, using a large encoder for short-term frames and a lightweight encoder for long-term temporal context to strike a favorable balance between accuracy and efficiency. The framework jointly extracts dense background features and sparse foreground features, enabling task-specific representations that reduce cumulative errors and provide richer information for downstream prediction and planning modules. HENet++ is compatible with diverse 3D feature extraction pipelines and supports multi-modal inputs, including camera and radar data. Extensive experiments demonstrate state-of-the-art performance on the nuScenes multi-task 3D perception benchmark, achieving the lowest collision rate on the nuScenes planning benchmark and higher PDMS on the NAVSIM benchmark.
Read the full abstract

All authors Zhongyu Xia, Zhiwei Lin, Yongtao Wang, Ming-Hsuan Yang

Computer Vision

GEWDiff: Geometric Enhanced Wavelet-based Diffusion Model for Hyperspectral Image Super-resolution

Improving the quality of hyperspectral images (HSIs), such as through super-resolution, is a crucial research area. However, generative modeling for HSIs presents several challenges. Due to their high spectral dimensionality, HSIs are too memory-intensive for direct input into conventional diffusion models. Furthermore, general generative models lack an understanding of the topological and geometric structures of ground objects in remote sensing imagery. In addition, most diffusion models optimize loss functions at the noise level, leading to a non-intuitive convergence behavior and suboptimal generation quality for complex data. To address these challenges, we propose a Geometric Enhanced Wavelet-based Diffusion Model (GEWDiff), a novel framework for reconstructing hyperspectral images at 4-times super-resolution. A wavelet-based encoder-decoder is introduced that efficiently compresses HSIs into a latent space while preserving spectral-spatial information. To avoid distortion during generation, we incorporate a geometry-enhanced diffusion process that preserves the geometric features. Furthermore, a multi-level loss function was designed to guide the diffusion process, promoting stable convergence and improved reconstruction fidelity. Our model demonstrated state-of-the-art results across multiple dimensions, including fidelity, spectral accuracy, visual realism, and clarity.
Read the full abstract

All authors Sirui Wang, Jiang He, Natàlia Blasco Andreo, Xiao Xiang Zhu

Computer Vision · Cross-listed from eess.IV

Task-Adaptive Low-Dose CT Reconstruction

Deep learning-based low-dose computed tomography reconstruction methods already achieve high performance on standard image quality metrics like peak signal-to-noise ratio and structural similarity index measure. Yet, they frequently fail to preserve the critical anatomical details needed for diagnostic tasks. This fundamental limitation hinders their clinical applicability despite their high metric scores. We propose a novel task-adaptive reconstruction framework that addresses this gap by incorporating a frozen pre-trained task network as a regularization term in the reconstruction loss function. Unlike existing joint-training approaches that simultaneously optimize both reconstruction and task networks, and risk diverging from satisfactory reconstructions, our method leverages a pre-trained task model to guide reconstruction training while still maintaining diagnostic quality. We validate our framework on a liver and liver tumor segmentation task. Our task-adaptive models achieve Dice scores up to 0.707, approaching the performance of full-dose scans (0.874), and substantially outperforming joint-training approaches (0.331) and traditional reconstruction methods (0.626). Critically, our framework can be integrated into any existing deep learning-based reconstruction model through simple loss function modification, enabling widespread adoption for task-adaptive optimization in clinical practice. Our codes are available at: https://github.com/itu-biai/task_adaptive_ct
Read the full abstract

All authors Necati Sefercioglu, Mehmet Ozan Unal, Metin Ertas, Isa Yildirim

Computer Vision

How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions

Text-to-image generative models often exhibit bias related to sensitive attributes. However, current research tends to focus narrowly on single-object prompts with limited contextual diversity. In reality, each object or attribute within a prompt can contribute to bias. For example, the prompt "an assistant wearing a pink hat" may reflect female-inclined biases associated with a pink hat. The neglected joint effects of the semantic binding in the prompts cause significant failures in current debiasing approaches. This work initiates a preliminary investigation on how bias manifests under semantic binding, where contextual associations between objects and attributes influence generative outcomes. We demonstrate that the underlying bias distribution can be amplified based on these associations. Therefore, we introduce a bias adherence score that quantifies how specific object-attribute bindings activate bias. To delve deeper, we develop a training-free context-bias control framework to explore how token decoupling can facilitate the debiasing of semantic bindings. This framework achieves over 10% debiasing improvement in compositional generation tasks. Our analysis of bias scores across various attribute-object bindings and token decorrelation highlights a fundamental challenge: reducing bias without disrupting essential semantic relationships. These findings expose critical limitations in current debiasing approaches when applied to semantically bound contexts, underscoring the need to reassess prevailing bias mitigation strategies.
Read the full abstract

Computer Vision · Cross-listed from cs.HC

Achieving Effective Virtual Reality Interactions via Acoustic Gesture Recognition based on Large Language Models

Natural and efficient interaction remains a critical challenge for virtual reality and augmented reality (VR/AR) systems. Vision-based gesture recognition suffers from high computational cost, sensitivity to lighting conditions, and privacy leakage concerns. Acoustic sensing provides an attractive alternative: by emitting inaudible high-frequency signals and capturing their reflections, channel impulse response (CIR) encodes how gestures perturb the acoustic field in a low-cost and user-transparent manner. However, existing CIR-based gesture recognition methods often rely on extensive training of models on large labeled datasets, making them unsuitable for few-shot VR scenarios. In this work, we propose the first framework that leverages large language models (LLMs) for CIR-based gesture recognition in VR/AR systems. Despite LLMs' strengths, it is non-trivial to achieve few-shot and zero-shot learning of CIR gestures due to their inconspicuous features. To tackle this challenge, we collect differential CIR rather than original CIR data. Moreover, we construct a real-world dataset collected from 10 participants performing 15 gestures across three categories (digits, letters, and shapes), with 10 repetitions each. We then conduct extensive experiments on this dataset using an LLM-adopted classifier. Results show that our LLM-based framework achieves accuracy comparable to classical machine learning baselines, while requiring no domain-specific retraining.
Read the full abstract