Computer Vision
Development and evaluation of CADe systems in low-prevalence setting: The RARE25 challenge for early detection of Barrett's neoplasia
Tim J.M. Jaspers, Francisco Caetano, Cris H.B. Claessens et al. (+8 more)
Computer-aided detection (CADe) of early neoplasia in Barrett's esophagus is a low-prevalence surveillance problem in which clinically relevant findings are rare. Although many CADe systems report strong performance on balanced or enriched
datasets, their behavior under realistic prevalence remains insufficiently characterized. The RARE25 challenge addresses this gap by introducing a large-scale, prevalence-aware
benchmark for neoplasia detection. It includes a public training set and a hidden test set reflecting real-world incidence. Methods were evaluated using operating-point-specific metrics emphasizing high sensitivity and accounting for prevalence. Eleven teams from seven countries submitted approaches using diverse architectures, pretraining, ensembling, and calibration strategies. While several methods achieved strong discriminative performance, positive predictive values remained low, highlighting the difficulty of low-prevalence detection and the risk of overestimating clinical utility when prevalence is ignored. All methods relied on fully supervised classification despite the dominance of normal findings, indicating a lack of prevalence-agnostic approaches such as anomaly detection or one-class learning. By releasing a public
dataset and a reproducible evaluation framework, RARE25 aims to support the development of CADe systems robust to prevalence shift and suitable for clinical surveillance workflows.
Read the full abstract ▾
All authors Tim J.M. Jaspers, Francisco Caetano, Cris H.B. Claessens, Carolus H.J. Kusters, Rixta A.H. van Eijck van Heslinga, Floor Slooter, Jacques J. Bergman, Peter H.N. De With, Martijn R. Jong, Albert J. de Groof, Fons van der Sommen
Computer Vision
Do Instance Priors Help Weakly Supervised Semantic Segmentation?
Anurag Das, Anna Kukleva, Xinting Hu et al. (+2 more)
Semantic
segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundational
segmentation model, i.e. Segment Anything Model (SAM), with weak labels, including coarse masks, scribbles, and points. SAM, originally designed for instance-based
segmentation, cannot be directly used for semantic
segmentation tasks. In this work, we identify specific challenges faced by SAM and determine appropriate components to adapt it for class-based
segmentation using weak labels. Specifically, SeSAM decomposes class masks into connected components, samples point
prompts along object skeletons, selects SAM masks using weak-label coverage, and iteratively refines labels using pseudo-labels, enabling SAM-generated masks to be effectively used for semantic
segmentation. Integrated with a semi-supervised learning framework, SeSAM balances ground-truth labels, SAM-based pseudo-labels, and high-confidence pseudo-labels, significantly improving
segmentation quality. Extensive experiments across multiple
benchmarks and weak annotation types show that SeSAM consistently outperforms weakly supervised baselines while substantially reducing annotation cost relative to fine supervision.
Read the full abstract ▾
All authors Anurag Das, Anna Kukleva, Xinting Hu, Yuki M. Asano, Bernt Schiele
Computer Vision
RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation
Shuang Zeng, Boxu Xie, Lei Zhu et al. (+6 more)
Deep learning has greatly advanced medical image
segmentation, but its success relies heavily on fully supervised learning, which requires dense annotations that are costly and time-consuming for 3D volumetric scans. Barely-supervised learning reduces annotation burden by using only a few labeled slices per volume. Existing methods typically propagate sparse annotations to unlabeled slices through
geometric continuity to generate pseudo-labels, but this strategy lacks semantic understanding, often resulting in low-quality pseudo-labels. Furthermore, medical image
segmentation is inherently a pixel-level visual understanding task, where accuracy fundamentally depends on the quality of local, fine-grained visual features. Inspired by this, we propose RADA, a novel Region-Aware Dual-encoder Auxiliary learning pipeline which introduces a dual-encoder framework pre-trained on Alpha-CLIP to extract fine-grained, region-specific visual features from the original images and limited annotations. The framework combines image-level fine-grained visual features with text-level semantic guidance, providing region-aware semantic supervision that bridges image-level semantics and pixel-level
segmentation. Integrated into a triple-view training framework, RADA achieves SOTA performance under extremely sparse annotation settings on LA2018, KiTS19 and LiTS, demonstrating robust generalization across diverse
datasets.
Read the full abstract ▾
All authors Shuang Zeng, Boxu Xie, Lei Zhu, Xinliang Zhang, Jiakui Hu, Zhengjian Yao, Yuanwei Li, Yuxing Lu, Yanye Lu
Computer Vision
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Camile Lendering, Erkut Akdag and Egor Bondarev
Accurate defect
segmentation is critical for industrial inspection, yet dense pixel-level annotations are rarely available. A common workaround is to convert inexpensive bounding boxes into pseudo-masks using foundation
segmentation models such as the Segment Anything Model (SAM). However, these pseudo-labels are systematically noisy on industrial surfaces, often hallucinating background structure while missing sparse defects. To address this limitation, a noise-robust box-to-pixel
distillation framework, Boxes2Pixels, is proposed that treats SAM as a noisy teacher rather than a source of ground-truth supervision. Bounding boxes are converted into pseudo-masks offline by SAM, and a compact student is trained with (i) a hierarchical decoder over frozen DINOv2 features for semantic stability, (ii) an auxiliary binary localization head to decouple sparse foreground discovery from class prediction, and (iii) a one-sided online self-correction mechanism that relaxes background supervision when the student is confident, targeting teacher false negatives. On a manually annotated wind turbine inspection
benchmark, the proposed Boxes2Pixels improves anomaly mIoU by +6.97 and binary IoU by +9.71 over the strongest baseline trained under identical weak supervision. Moreover, online self-correction increases the binary recall by +18.56, while the model employs 80% fewer trainable parameters. Code is available at https://github.com/CLendering/Boxes2Pixels.
Read the full abstract ▾
Computer Vision
rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training
Tianyang Dai, Ming Chang, Yan Chen et al. (+1 more)
Unsupervised remote photoplethysmography (rPPG) promises to leverage unlabeled
video data, but its potential is hindered by a critical challenge: training on low-quality "in-the-wild"
videos severely degrades model performance. An essential step missing here is to assess the suitability of the
videos for rPPG model learning before using them for the task. Existing
video quality assessment (VQA) methods are mainly designed for human perception and not directly applicable to the above purpose. In this work, we propose rPPG-VQA, a novel framework for assessing
video suitability for rPPG. We integrate signal-level and scene-level analyses and design a dual-branch assessment architecture. The signal-level branch evaluates the physiological signal quality of the
videos via robust signal-to-noise ratio (SNR) estimation with a multi-method consensus mechanism, and the scene-level branch uses a
multimodal large
language model (MLLM) to identify interferences like motion and unstable lighting. Furthermore, we propose a two-stage adaptive sampling (TAS) strategy that utilizes the quality score to curate optimal training
datasets. Experiments show that by training on large-scale, "in-the-wild"
videos filtered by our framework, we can develop unsupervised rPPG models that achieve a substantial improvement in accuracy on standard
benchmarks. Our code is available at https://github.com/Tianyang-Dai/rPPG-VQA.
Read the full abstract ▾
All authors Tianyang Dai, Ming Chang, Yan Chen, Yang Hu
Computer Vision
Hierarchical Textual Knowledge for Enhanced Image Clustering
Yijie Zhong, Yunfan Gao, Weipeng Jiang et al. (+1 more)
Image clustering aims to group images in an unsupervised fashion. Traditional methods focus on knowledge from visual space, making it difficult to distinguish between visually similar but semantically different classes. Recent advances in
vision-
language models enable the use of textual knowledge to enhance image clustering. However, most existing methods rely on coarse class labels or simple nouns, overlooking the rich conceptual and attribute-level semantics embedded in textual space. In this paper, we propose a knowledge-enhanced clustering (KEC) method that constructs a hierarchical concept-attribute structured knowledge with the help of large
language models (LLMs) to guide clustering. Specifically, we first condense redundant textual labels into abstract concepts and then automatically extract discriminative attributes for each single concept and similar concept pairs, via structured
prompts to LLMs. This knowledge is instantiated for each input image to achieve the knowledge-enhanced features. The knowledge-enhanced features with original visual features are adapted to various downstream clustering
algorithms. We evaluate KEC on 20 diverse
datasets, showing consistent improvements across existing methods using additional textual knowledge. KEC without training outperforms zero-shot CLIP on 14 out of 20
datasets. Furthermore, the naive use of textual knowledge may harm clustering performance, while KEC provides both accuracy and robustness.
Read the full abstract ▾
All authors Yijie Zhong, Yunfan Gao, Weipeng Jiang, Haofen Wang
Computer Vision
Naka-GS: Naka-Guided Chroma Correction and Point-Prior Compaction for Low-Light 3D Gaussian Splatting
Runyu Zhu, SiXun Dong, Zhiqiang Zhang et al. (+3 more)
Low-light inputs obscure scene content, distort color, and corrupt
geometric priors, substantially degrading 3D Gaussian Splatting. Although image enhancement can recover visibility, it often introduces chromatic deviations and fine-scale artifacts that propagate through multi-view reconstruction. Moreover, dense point priors can further amplify these errors and increase optimization cost. To address the coupled challenges, we present Naka-GS, a low-light 3DGS framework that jointly improves observations and Gaussian initialization while retaining the standard 3DGS renderer and training objective. Our Naka-Guided Chroma Correction treats a fixed bionic response as a photometric anchor and learns bounded, frequency-decoupled luminance and chromatic corrections, preserving fine structures while suppressing residual color and boundary artifacts. The corrected views are reconstructed into dense scene priors, which a lightweight, non-learned Point-Prior Compaction Module refines through voxel pooling and distance-adaptive progressive
pruning. On eight scene-disjoint RealX3D scenes, Naka-GS achieves 20.735~dB PSNR, 0.7408 SSIM, and 0.3340 LPIPS. PPM reduces initialization from 1.00M to 59.52K points and shortens average 3DGS optimization time by 37.7%.The code is available at https://github.com/RunyuZhu/Naka-GS
Read the full abstract ▾
All authors Runyu Zhu, SiXun Dong, Zhiqiang Zhang, Qingxia Ye, Rongjun Qin, Zhihua Xu
Computer Vision
Hyper-FEOD: Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoE
Wei Bao, Yuehan Wang, Tianhang Zhou et al. (+1 more)
The integration of frame-based RGB cameras with event streams constitutes a promising paradigm for robust object detection under challenging dynamic conditions. Nevertheless, effectively modeling intricate multi-modal interactions and reconciling the semantic heterogeneity between RGB and event data remain formidable challenges for high-precision detection. In this paper, we present Hyper-FEOD, a novel high-performance detection framework that synergistically strengthens cross-modal representation learning through two core hypergraph-driven components. Specifically, we first design a Sparse Hypergraph-enhanced Cross-Modal Fusion (SHCF) module that exploits event activity cues to identify motion-critical sparse
tokens and performs high-order relational
reasoning through hypergraph modeling. This design effectively captures intricate high-order dependencies and rich contextual correlations across modalities. Second, we develop a Fine-Grained Mixture-of-Experts (FG-MoE) module tailored to handle the heterogeneous semantic demands arising from distinct visual regions. By deploying specialized hypergraph experts with varying hyperedge connectivity pattern and incorporating a spatial gating mechanism, FG-MoE adaptively routes features to enable precise enhancement at target regions. Coupled with an auxiliary router loss, the proposed framework ensures stable end-to-end training and optimal feature refinement. Comprehensive experiments conducted on widely-adopted RGB-Event
benchmarks show that Hyper-FEOD delivers superior detection performance and consistently outperforms existing state-of-the-art approaches by a notable margin.
Read the full abstract ▾
All authors Wei Bao, Yuehan Wang, Tianhang Zhou, Siqi Li
Computer Vision · Cross-listed from cs.RO
ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation
Arjun Bhardwaj, Maximum Wilder-Smith, Mayank Mittal et al. (+2 more)
In-hand object reorientation requires precise estimation of the object pose to handle complex task dynamics. While RGB sensing offers rich semantic cues for pose tracking, existing solutions rely on multi-camera setups or costly ray tracing. We present a sim-to-real framework for
monocular RGB in-hand reorientation that integrates 3D Gaussian Splatting (3DGS) to bridge the visual sim-to-real gap. Our key insight is performing domain randomization in the Gaussian representation space: by applying physically consistent, pre-rendering augmentations to 3D Gaussians, we generate photorealistic, randomized visual data for object pose estimation. The manipulation policy is trained using curriculum-based reinforcement learning with teacher-student
distillation, enabling efficient learning of complex behaviors. Importantly, both perception and control models can be trained independently on consumer-grade hardware, eliminating the need for large compute clusters. Experiments show that the pose
estimator trained with 3DGS data outperforms those trained using conventional rendering data in challenging visual environments. We validate the system on a physical multi-fingered hand equipped with an RGB camera, demonstrating robust reorientation of five diverse objects even under challenging lighting conditions. Our results highlight Gaussian splatting as a practical path for RGB-only dexterous manipulation. For
videos of the hardware deployments and additional supplementary materials, please refer to the project website: https://rffr.leggedrobotics.com/works/viserdex/
Read the full abstract ▾
All authors Arjun Bhardwaj, Maximum Wilder-Smith, Mayank Mittal, Vaishakh Patil, Marco Hutter
Computer Vision
BoxTuning: Directly Injecting the Object Box for Multimodal Model Fine-Tuning
Zekun Qian, Ruize Han and Wei Feng
Object-level spatial-temporal understanding is essential for
video question answering, yet existing
multimodal large
language models (MLLMs) encode frames holistically and lack explicit mechanisms for fine-grained object grounding. Recent work addresses this by serializing bounding box coordinates as text
tokens, but this text-coordinate paradigm suffers from a fundamental modality mismatch: object information is inherently visual, yet encoding it as text incurs a high
token cost that forces aggressive temporal downsampling. We propose BoxTuning, which resolves this mismatch by injecting object spatial-temporal information directly into the visual modality. Colored bounding boxes and trajectory trails are rendered onto
video frames as visual
prompts, with only a concise color-to-object legend retained as text. This reduces the
token cost significantly, achieving 87-93% text
token reduction in practice. It also preserves full temporal resolution, where the trajectory trails further encode inter-frame motion direction and speed within each keyframe, recovering fine-grained dynamics that text-coordinate methods are forced to discard. Experimental results on five
video QA
benchmarks (CLEVRER, Perception Test,
STAR, NExT-QA, IntentQA) show that BoxTuning surpasses text-coordinate baselines on spatially oriented tasks and nearly eliminates the accuracy degradation observed on
reasoning-centric tasks, establishing visual prompting as a more natural and efficient paradigm for conveying object information to
video MLLMs.
Read the full abstract ▾
Computer Vision
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
Yueying Li, Fengxiang Wang, Yan Li et al. (+3 more)
Multimodal Large
Language Models (MLLMs) have demonstrated immense potential in Earth observation. However, the massive visual
tokens generated when processing Ultra-High-Resolution (UHR) imagery introduce prohibitive computational overhead, severely bottlenecking their inference efficiency. Existing visual
token compression methods predominantly adopt static and uniform compression strategies, neglecting the inherent "Semantic-
Geometric Duality" in remote sensing interpretation tasks. Specifically, object semantic tasks focus on the abstract semantics of objects and benefit from aggressive background
pruning, whereas scene
geometric tasks critically rely on the integrity of spatial
topology. To address this challenge, we propose DualComp, a task-adaptive dual-stream
token compression framework. Dynamically guided by a lightweight pre-trained router, DualComp decouples feature processing into two dedicated pathways. In the object semantic stream, the Spatially-Contiguous Semantic Aggregator (SCSA) utilizes size-adaptive clustering to aggregates redundant background while protecting small object. In the scene
geometric stream, the Instruction-Guided Structure Recoverer (IGSR) introduces a greedy path-tracing
topology completion mechanism to reconstruct spatial skeletons. Experiments on the UHR remote sensing
benchmark XLRS-Bench demonstrate that DualComp accomplishes high-fidelity remote sensing interpretation at an exceptionally low computational cost, achieving simultaneous improvements in both efficiency and accuracy.
Read the full abstract ▾
All authors Yueying Li, Fengxiang Wang, Yan Li, Mingshuo Chen, Mengying Zhao, Long Lan
Computer Vision · Cross-listed from cs.LG
Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning
Linjie Li, Huiyu Xiao, Jiarui Cao et al. (+2 more)
Class-incremental learning (CIL) aims to continuously accumulate knowledge from a stream of tasks and construct a unified classifier over all seen classes. Although pretrained models (PTMs) have shown promising performance in CIL, they still struggle with the
entanglement of multi-task subspaces, leading to catastrophic forgetting when task routing parameters are poorly calibrated or task-level representations are rigidly fixed. To address this issue, we propose a novel
Quantum-Gated Task-interaction Knowledge
Distillation (QKD) framework that leverages
quantum gating to guide inter-task knowledge transfer. Specifically, we introduce a
quantum-gated task modulation gating mechanism to model the relational dependencies among task
embedding, dynamically capturing the sample-to-task relevance for both joint training and inference across streaming tasks. Guided by the
quantum gating outputs, we perform task-interaction knowledge
distillation guided by these task-
embedding-level correlation weights from old to new adapters, enabling the model to bridge the representation gaps between independent task subspaces. Extensive experiments demonstrate that QKD effectively mitigates forgetting and achieves state-of-the-art performance.
Read the full abstract ▾
All authors Linjie Li, Huiyu Xiao, Jiarui Cao, Zhenyu Wu, Yang Ji
Computer Vision
OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video
Junfu Pu, Yuxin Chen, Teng Wang et al. (+1 more)
Current
multimodal large
language models (MLLMs) have demonstrated remarkable capabilities in short-form
video understanding, yet translating long-form cinematic
videos into detailed, temporally grounded scripts remains a significant challenge. This paper introduces the novel
video-to-script (V2S) task, aiming to generate hierarchical, scene-by-scene scripts encompassing character actions, dialogues, expressions, and audio cues. To facilitate this, we construct a first-of-its-kind human-annotated
benchmark and propose a temporally-aware hierarchical evaluation framework. Furthermore, we present OmniScript, an 8B-parameter omni-modal (audio-visual)
language model tailored for long-form narrative comprehension. OmniScript is trained via a progressive pipeline that leverages chain-of-thought supervised fine-tuning for plot and character
reasoning, followed by reinforcement learning using temporally segmented rewards. Extensive experiments demonstrate that despite its parameter efficiency, OmniScript significantly outperforms larger open-source models and achieves performance comparable to state-of-the-art proprietary models, including Gemini 3-Pro, in both temporal localization and multi-field semantic accuracy.
Read the full abstract ▾
All authors Junfu Pu, Yuxin Chen, Teng Wang, Ying Shan
Computer Vision
Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction
Zeyi Ren, Jialin Dong, Wei Zuo et al. (+4 more)
Large-scale three-dimensional (3D) scene reconstruction in low-altitude intelligent networks (LAIN) demands highly efficient wireless image transmission. However, existing schemes struggle to balance severe pilot overhead with the transmission accuracy required to maintain reconstruction fidelity. To strike a balance between efficiency and reliability, this paper proposes a novel deep learning-based end-to-end (E2E) transceiver design that integrates 3D Gaussian Splatting (3DGS) directly into the training process. By jointly optimizing the communication modules via the combined 3DGS rendering loss, our approach explicitly improves scene recovery quality. Furthermore, this task-driven framework enables the use of a sparse pilot scheme, significantly reducing transmission overhead while maintaining robust image recovery under low-altitude channel conditions. Extensive experiments on real-world aerial image
datasets demonstrate that the proposed E2E design significantly outperforms existing baselines, delivering superior transmission performance and accurate 3D scene reconstructions.
Read the full abstract ▾
All authors Zeyi Ren, Jialin Dong, Wei Zuo, Yikun Wang, Bingyang Cheng, Sheng Zhou, Zhisheng Niu
Computer Vision
CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation
Rongjia Yu, Tong Jia, Hao Wang et al. (+4 more)
Monocular depth estimation is a fundamental yet challenging task in computer
vision, especially under complex conditions such as textureless surfaces, transparency, and specular reflections. Recent
diffusion-based approaches have significantly advanced performance by reformulating depth prediction as a denoising process in the latent space. However, existing methods rely solely on RGB inputs, which often lack sufficient cues in challenging regions. In this work, we present CDPR - Cross-modal
Diffusion with Polarization for Reliable
Monocular Depth Estimation - a novel
diffusion-based framework that integrates physically grounded polarization priors to enhance estimation robustness. Specifically, we encode both RGB and polarization (AoLP/DoLP) images into a shared latent space via a pre-trained Variational Autoencoder (VAE), and dynamically fuse multi-modal information through a learnable confidence-aware gating mechanism. This fusion module adaptively suppresses noisy signals in polarization inputs while preserving informative cues, particularly around reflective or transparent surfaces, and provides the integrated latent representation for subsequent
monocular depth estimation. Beyond depth estimation, we further verify that our framework can be easily generalized to surface normal prediction with minimal modification, showcasing its scalability to general polarization-guided dense prediction tasks. Experiments on both synthetic and real-world
datasets validate that CDPR significantly outperforms RGB-only baselines in challenging regions while maintaining competitive performance in standard scenes.
Read the full abstract ▾
All authors Rongjia Yu, Tong Jia, Hao Wang, Xiaofang Li, Xiao Yang, Zinuo Zhang, Cuiwei Liu
Computer Vision
LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning
Linjie Li, Zhenyu Wu, Huiyu Xiao et al. (+1 more)
Prompt-based class-incremental learning methods typically construct a
prompt pool consisting of multiple trainable key-
prompts and perform instance-level matching to select the most suitable
prompt embeddings, which has shown promising results. However, existing approaches face several limitations, including fixed
prompt pools, manual selection of
prompt embeddings, and strong reliance on the pretrained backbone for
prompt selection. To address these issues, we propose a Layer-importance guided Dual Expandable
Prompt Pool (LDEPrompt), which enables adaptive layer selection as well as dynamic freezing and expansion of the
prompt pool. Extensive experiments on widely used class-incremental learning
benchmarks demonstrate that LDEPrompt achieves state-of-the-art performance, validating its effectiveness and scalability.
Read the full abstract ▾
All authors Linjie Li, Zhenyu Wu, Huiyu Xiao, Yang Ji
Computer Vision
Structured State-Space Regularization for Generation-Friendly Image Tokenization
Jinsung Lee, Jaemin Oh, Namhun Kim et al. (+3 more)
Image tokenizers play a central role in modern generative models, where the structure of the latent space critically determines the downstream generation performance. A key but underexplored property of effective latent representations is spectral organization, the ability to encode information across frequency components. In this work, we introduce structured state-space regularization, a principled approach to inducing spectral structure in latent spaces. We derive a regularization objective by revisiting state-space models (SSMs) as systems mimicking a basis function's behavior. This perspective reveals that hidden states of SSMs are induced to capture the frequency components, resulting in a novel regularizer that enforces the latent space to capture spectral structure of images. Experiments demonstrate that our regularizer improves the generative performance of image tokenizers while incurring only minimal loss in their reconstruction fidelity.
Read the full abstract ▾
All authors Jinsung Lee, Jaemin Oh, Namhun Kim, Dongwon Kim, Byung-Jun Yoon, Suha Kwak
Computer Vision
FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling
Dawei Guan, Di Yang, Chengjie Jin et al. (+1 more)
Text-to-motion generation is driven by learning motion representations for semantic
alignment with
language. Existing methods rely on either continuous or discrete motion representations. However, continuous representations entangle semantics with dynamics, while discrete representations lose fine-grained motion details. In this context, we propose FlowCoMotion, a novel motion generation framework that unifies both treatments from a modeling perspective. Specifically, FlowCoMotion employs
token-latent coupling to capture both semantic content and high-fidelity motion details. In the latent branch, we apply multi-view
distillation to regularize the continuous latent space, while in the
token branch we use discrete temporal resolution quantization to extract high-level semantic cues. The motion latent is then obtained by combining the representations from the two branches through a
token-latent coupling network. Subsequently, a velocity field is predicted based on the textual conditions. An ODE solver integrates this velocity field from a simple prior, thereby guiding the sample to the potential state of the target motion. Extensive experiments show that FlowCoMotion achieves competitive performance on text-to-motion
benchmarks, including HumanML3D and SnapMoGen.
Read the full abstract ▾
All authors Dawei Guan, Di Yang, Chengjie Jin, Jiangtao Wang
Computer Vision
RefGlitch-Bench: A Benchmark for Reference-based Gameplay Glitch Detection with Vision-Language Models
Yakun Yu, Ashley Wiens, Adrián Barahona-Ríos et al. (+4 more)
Visual glitches in
video games degrade player experience and perceived quality, yet manual quality assurance cannot keep pace with the growing test surface of modern game development. Prior automation efforts, particularly those using
vision-
language models (VLMs), largely operate on isolated frames without sufficient context to judge whether a glitch is present. We introduce RefGlitch-Bench, a
benchmark for reference-based
video game glitch detection with VLMs. The key idea is to formulate glitch detection as an explicit within-
video comparison problem: given a test frame, a reference frame provides a visual baseline that helps the model distinguish true glitches from benign visual variation. RefGlitch-Bench includes a controlled synthetic
dataset with five injected glitch types and manually annotated reference/test frame pairs, enabling an oracle-reference evaluation that isolates the potential benefit of reference guidance. We further establish four initial baselines for automatically selecting references from earlier frames in the same
video, with LastCleanFrame performing best and transferring across VLMs. Finally, we evaluate automatic reference guidance on real-world gameplay data, where it improves frame-level glitch detection beyond the controlled setting while revealing reference reliability and error propagation as key challenges. Code and data are available at: https://github.com/PipiZong/RefGlitch-Bench.git.
Read the full abstract ▾
All authors Yakun Yu, Ashley Wiens, Adrián Barahona-Ríos, Benedict Wilkins, Saman Zadtootaghaj, Nabajeet Barman, Cor-Paul Bezemer
Computer Vision
MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling
Mingyang Li, Brian Lee, Rui Zuo et al. (+3 more)
High-definition (HD) mapping tasks, which perform lane detections and predictions, are extremely challenging due to non-ideal conditions such as view occlusions, distant lane visibility, and adverse weather conditions. Those conditions often result in compromised lane detection accuracy and reduced reliability within autonomous driving systems. To address these challenges, we introduce MapATM, a novel deep neural network that effectively leverages historical actor trajectory information to improve lane detection accuracy, where actors refer to moving vehicles. By utilizing actor trajectories as structural priors for road geometry, MapATM achieves substantial performance enhancements, notably increasing AP by 4.6 for lane dividers and mAP by 2.6 on the challenging NuScenes
dataset, representing relative improvements of 10.1% and 6.1%, respectively, compared to strong baseline methods. Extensive qualitative evaluations further demonstrate MapATM's capability to consistently maintain stable and robust map reconstruction across diverse and complex driving scenarios, underscoring its practical value for autonomous driving applications.
Read the full abstract ▾
All authors Mingyang Li, Brian Lee, Rui Zuo, Brent Bacchus, Priyantha Mudalige, Qinru Qiu
Computer Vision
ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation
Suyoung Kim, Sunghyun Wee, Hyeonjin Kim et al. (+3 more)
Rotation-based Post-Training Quantization (PTQ) has emerged as a promising solution for mitigating activation outliers in the quantization of Large
Language Models (LLMs). Global rotation methods achieve inference efficiency by fusing activation rotations into
attention and FFN blocks, but suffer from limited expressivity as they are constrained to use a single learnable rotation
matrix across all layers. To tackle this, layer-wise transformation methods emerged, achieving superior accuracy through localized adaptation. However, layer-wise methods cannot fuse activation rotation
matrices into weights, requiring online computations and causing significant overhead. In this paper, we propose ReSpinQuant, a quantization framework that resolves such overhead by leveraging offline activation rotation fusion and matching basis using efficient residual subspace rotation. This design reconciles the high expressivity of layer-wise adaptation with only negligible inference overhead. Extensive experiments on W4A4 and W3A3 quantization demonstrate that ReSpinQuant achieves state-of-the-art performance, outperforming global rotation methods and matching the accuracy of computationally expensive layer-wise methods with minimal overhead.
Read the full abstract ▾
All authors Suyoung Kim, Sunghyun Wee, Hyeonjin Kim, Kyomin Hwang, Hyunho Lee, Nojun Kwak
Computer Vision
Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net
Shimon Murai, Teppei Kurita, Ryuta Satoh et al. (+1 more)
We present a lightweight two-stage framework for low-light image enhancement (LLIE) that achieves competitive perceptual quality with significantly fewer parameters than existing methods. Our approach combines frozen
algorithm-based preprocessing with a compact U-Net built entirely from depthwise-separable convolutions. The preprocessing normalizes the input distribution by providing complementary brightness-corrected views, enabling the trainable network to focus on residual color correction. Our method achieved 3rd place in the CVPR 2026 NTIRE Efficient Low-Light Image Enhancement Challenge. We further provide extended
benchmarks and ablations to demonstrate the general effectiveness of our methods.
Read the full abstract ▾
All authors Shimon Murai, Teppei Kurita, Ryuta Satoh, Yusuke Moriuchi
Computer Vision · Cross-listed from cs.LG
A Faster Path to Continual Learning
Wei Li, Hangjie Yuan, Zixiang Zhao et al. (+3 more)
Continual Learning (CL) aims to train neural networks on a dynamic stream of tasks without forgetting previously learned knowledge. Among optimization-based approaches, C-Flat has emerged as a promising solution due to its plug-and-play nature and its ability to encourage uniformly low-loss regions for both new and old tasks. However, C-Flat requires three additional gradient computations per iteration, imposing substantial overhead on the optimization process. In this work, we propose C-Flat Turbo, a faster yet stronger optimizer that significantly reduces the training cost. We show that the gradients associated with first-order flatness contain direction-invariant components relative to the proxy-model gradients, enabling us to skip redundant gradient computations in the perturbed ascent steps. Moreover, we observe that these flatness-promoting gradients progressively stabilize across tasks, which motivates a linear scheduling strategy with an adaptive trigger to allocate larger turbo steps for later tasks. Experiments show that C-Flat Turbo is 1.0$\times$ to 1.25$\times$ faster than C-Flat across a wide range of CL methods, while achieving comparable or even improved accuracy.
Read the full abstract ▾
All authors Wei Li, Hangjie Yuan, Zixiang Zhao, Borui Kang, Ziwei Liu, Tao Feng
Computer Vision
Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization
Renyu Li, Vladimir Kirilenko, Yao You et al. (+1 more)
Fine-tuning object detection (OD) models on combined
datasets assumes annotation compatibility, yet
datasets often encode conflicting spatial definitions for semantically equivalent categories. We propose an agentic label harmonization workflow that uses a
vision-
language model to reconcile both category semantics and bounding box granularity across heterogeneous sources before training. We evaluate on document layout detection as a challenging case study, where annotation standards vary widely across corpora. Without harmonization, naïve mixed-
dataset fine-tuning degrades a pretrained RT-DETRv2 detector: on SCORE-Bench, which measures how accurately the full document conversion pipeline reproduces ground-truth structure, table TEDS drops from 0.800 to 0.750. Applied to two corpora whose 16 and 10 category taxonomies share only 8 direct correspondences, harmonization yields consistent gains across content fidelity, table structure, and spatial consistency: detection F-score improves from 0.860 to 0.883, table TEDS improves to 0.814, and mean bounding box overlap drops from 0.043 to 0.016. Representation analysis further shows that harmonized training produces more compact and separable post-decoder
embeddings, confirming that annotation inconsistency distorts the learned feature space and that resolving it before training restores representation structure.
Read the full abstract ▾
All authors Renyu Li, Vladimir Kirilenko, Yao You, Crag Wolfe
Computer Vision
EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates
Weikun Peng, Denys Iliash and Manolis Savva
We present EgoFun3D, a coordinated task formulation,
dataset, and
benchmark for modeling interactive 3D objects from
egocentric videos. Interactive objects are of high interest for
embodied AI but scarce, making modeling from readily available real-world
videos valuable. Our task focuses on obtaining simulation-ready interactive 3D objects from
egocentric video input. While prior work largely focuses on articulations, we capture general cross-part functional mappings (e.g., rotation of stove knob controls stove burner temperature) through function templates, a structured computational representation. Function templates enable precise evaluation and direct compilation into executable code across simulation platforms. To enable comprehensive benchmarking, we introduce a
dataset of 517
egocentric videos featuring challenging real-world interactions with paired 3D geometry,
segmentation over 2D and 3D, articulation and function template annotations. To tackle the task, we propose a 4-stage pipeline consisting of: 2D part
segmentation, reconstruction, articulation estimation, and function template inference. Comprehensive benchmarking shows that the task is challenging for off-the-shelf methods, highlighting avenues for future work.
Read the full abstract ▾
Computer Vision
Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images
Zheng Jiang, Yiming Chen, Nan He et al. (+4 more)
Recent
multimodal large
language models (MLLMs) support Thinking with Images, invoking visual tools such as zooming and cropping to inspect image regions during inference. Yet these systems remain brittle in fine-grained
reasoning: to acquire a decisive detail, a model must ground its
attention on the correct region, but knowing which region is correct presupposes having already observed that detail. We identify this circular dependency as the grounding paradox, show that grounding errors are rarely self-corrected within a single trajectory—once a misleading region is inspected, all subsequent
reasoning conditions on that observation and the error propagates to the final answer—and observe that because each trajectory constructs its own evidence, answer-level aggregation discards the very information that distinguishes trajectories. We propose Test-Time Scaling over Perception (TTSP), a closed-loop framework that treats perception as the unit of scalable inference and allocates compute along two axes:
Entropy-Gated Perceptual Exploration samples diverse trajectories and uses critical-
token entropy to withhold evidence the model cannot commit to, while Evidence-Guided Iterative Refinement distills validated observations into a correctable Evidence Ledger that steers later rounds to re-inspect unresolved regions. Across high-resolution and general
multimodal benchmarks, TTSP consistently outperforms strong test-time scaling baselines, while improving grounding quality with favorable
token efficiency.
Read the full abstract ▾
All authors Zheng Jiang, Yiming Chen, Nan He, Jiahui Chen, Chaoyang Li, Houde Qian, Lifeng Sun
Computer Vision
UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling
Weiyuan He, Chen Wu, Pengwen Dai et al. (+6 more)
Ultra-high-definition (UHD)
video denoising requires simultaneously suppressing complex spatio-temporal degradations, preserving fine textures and chromatic stability, and maintaining efficient full-resolution 4K deployment. In this paper, we propose UHD-GPGNet, a Gaussian-process-guided local spatio-temporal denoising framework that addresses these requirements jointly. Rather than relying on implicit feature learning alone, the method estimates sparse GP posterior statistics over compact spatio-temporal descriptors to explicitly characterize local degradation response and uncertainty, which then guide adaptive temporal-detail fusion. A structure-color collaborative reconstruction head decouples luminance, chroma, and high-frequency correction, while a heteroscedastic objective and overlap-tiled inference further stabilize optimization and enable
memory-bounded 4K deployment. Experiments on UVG and RealisVideo-4K show that UHD-GPGNet achieves competitive restoration fidelity with substantially fewer parameters than existing methods, enables real-time full-resolution 4K inference with significant speedup over the closest quality competitor, and maintains robust performance across a multi-level mixed-degradation schedule.A real-world study on phone-captured 4K
video further confirms that the model, trained entirely on synthetic degradation, generalizes to unseen real sensor noise and improves downstream object detection under challenging conditions.
Read the full abstract ▾
All authors Weiyuan He, Chen Wu, Pengwen Dai, Wei Wang, Dianjie Lu, Guijuan Zhang, Linwei Fan, Yongzhen Wang, Zhuoran Zheng
Computer Vision
Byte-level generative predictions for forensics multimedia carving
Jaewon Lee, Md Eimran Hossain Eimon, Avinash Srinivasan et al. (+1 more)
Digital forensic investigations often face significant challenges when recovering fragmented multimedia files that lack file system metadata. While traditional file carving relies on signatures and discriminative deep learning models for fragment classification, these methods cannot reconstruct or predict missing data. We propose a generative approach to multimedia carving using bGPT, a byte-level
transformer designed for next-byte prediction. By feeding partial BMP image data into the model, we simulate the generation of likely fragment continuations. We evaluate the fidelity of these predictions using different metrics, namely, cosine similarity, structural similarity index (SSIM), chi-square distance, and Jensen-Shannon divergence (JSD). Our findings demonstrate that generative models can effectively predict byte-level patterns to support fragment matching in unallocated disk space.
Read the full abstract ▾
All authors Jaewon Lee, Md Eimran Hossain Eimon, Avinash Srinivasan, Hari Kalva
Computer Vision
Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labeling
Takahiko Furuya
Semantic
segmentation of 3D point cloud scenes is a crucial task for various applications. In real-world scenarios, training
segmentation models often faces three concurrent forms of data insufficiency: scarcity of training scenes, scarcity of point-level annotations, and absence of 2D image sequences from which point clouds were reconstructed. Existing data-efficient
algorithms typically address only one or two of these challenges, leaving the joint treatment of all three unexplored. This paper proposes a data-efficient training framework specifically designed to address the three forms of data insufficiency. Our proposed
algorithm, called Point pseudo-Labeling via Open-Vocabulary Image
Segmentation (PLOVIS), leverages an open-vocabulary image
segmentation model as a pseudo label generator to compensate for the lack of training data. PLOVIS creates 2D images for pseudo-labeling directly from training 3D point clouds, eliminating the need for 2D image sequences. To mitigate the inherent noise and class imbalance in pseudo labels, we introduce a two-stage filtering of pseudo labels combined with a class-balanced
memory bank for effective training. The two-stage filtering mechanism first removes low-confidence pseudo labels, then discards likely incorrect pseudo labels, thereby enhancing the quality of pseudo labels. Experiments on four
benchmark datasets, i.e., ScanNet, S3DIS, Toronto3D, and Semantic3D, under realistic data-scarce conditions (a few tens of training 3D scenes, each annotated with only <100 3D points) demonstrate that PLOVIS consistently outperforms existing methods including standard fine-tuning strategies and state-of-the-art weakly supervised learning
algorithms. Code will be made publicly available.
Read the full abstract ▾
Computer Vision
Towards Realistic 3D Emission Materials: Dataset, Baseline, and Evaluation for Emission Texture Generation
Zhiyuan Zhang, Zijian Zhou, Linjun Li et al. (+3 more)
3D texture generation is receiving increasing
attention, as it enables the creation of realistic and aesthetic texture materials for untextured 3D meshes. However, existing 3D texture generation methods are limited to producing only a few types of non-emissive PBR materials (e.g., albedo, metallic maps and roughness maps), making them difficult to replicate highly popular styles, such as cyberpunk, failing to achieve effects like realistic LED emissions. To address this limitation, we propose a novel task, emission texture generation, which enables the synthesized 3D objects to faithfully reproduce the emission materials from input reference images. Our key contributions include: first, We construct the Objaverse-Emission
dataset, the first
dataset that contains 40k 3D assets with high-quality emission materials. Second, we propose EmissionGen, a novel baseline for the emission texture generation task. Third, we define detailed evaluation metrics for the emission texture generation task. Our results demonstrate significant potential for future industrial applications.
Dataset will be available at https://github.com/yx345kw/EmissionGen.
Read the full abstract ▾
All authors Zhiyuan Zhang, Zijian Zhou, Linjun Li, Long Chen, Hao Tang, Yichen Gong