Computer Vision
Jongoh Jeong, Hoyong Kwon, Minseok Kim et al. (+1 more)
Dataset distillation compresses large training sets into compact synthetic
datasets while preserving downstream performance. As modern systems increasingly operate on paired
vision-
language inputs,
multimodal distillation must preserve representation quality and cross-modal
alignment under tight compute and
memory budgets, yet prior methods often require heavy computes and overlook their correlations. To address this, we present
Multimodal Distribution Matching (MDM), a geometry-aware framework for efficient and generalizable
multimodal distillation. Specifically, MDM integrates complementary components at the data, model, and loss levels. At the data level, it initializes synthetic image-text pairs by sampling from clusters in the joint
embedding space. At the model level, it forms a mixed teacher by interpolating independently fine-tuned models in weight space according to their angular deviation from the pretrained anchor. At the loss level, it matches joint distributions on the unit hypersphere using a geometry-aware matching objective that exploits the joint features in the cross-modal agreement and discrepancy directions along with symmetric contrastive learning. Across image-text
retrieval benchmarks with cross-architecture evaluation, MDM yields compact synthetic sets that preserve
multimodal semantics, substantially reduce
distillation cost, and remain robust across architectures.
Read the full abstract ▾
All authors Jongoh Jeong, Hoyong Kwon, Minseok Kim, Kuk-Jin Yoon
Computer Vision
PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction
Yu Luo, Xiaogang Zhu, Shan Zeng et al. (+4 more)
Accurate crop yield prediction is crucial for sustainable agriculture and global food security. While existing methods are predominantly developed for single-crop prediction, they often struggle to generalize across diverse crop types, without addressing the unique crop phenological responses that are dynamically modulated by complex weather patterns. In this paper, we propose PhenoYieldNet, a multi-crop yield prediction framework that learns crop-specific phenology by explicitly modeling their responses with temporal drivers. Specifically, we develop a crop-aware temporal decoder consisting of a Crop Phenology Bank (CPB) and a Crop Phenology
Attention (CPA) module. The CPB integrates a set of learnable
embeddings, which leverage a query to guide the CPA module to learn the most relevant phenology patterns for the specific crop. And the CPA module explicitly captures multi-scale trend and variation components to construct temporal contexts, enabling the model to dynamically adjust the
attention across different phenological stages. To learn robust and generalizable features for multi-crop prediction, the encoder is initialized with a pre-trained foundation model, and further adapted via a self-supervised Temporal Contrastive Adaptation strategy to align with agricultural temporal dynamics. Extensive experiments conducted on multi-crop
datasets indicate that our proposed method significantly outperforms state-of-the-art methods, exhibiting strong generalization capabilities across different regions and crops.
Read the full abstract ▾
All authors Yu Luo, Xiaogang Zhu, Shan Zeng, Wei Xiang, Thomas Francis Bishop, Zhiyong Wang, Kun Hu
Computer Vision
Rethinking Transfer Learning for Industrial Inspection: DINOv3 vs. ImageNet Pretraining Across RGB and X-ray Tasks
Mehdi Gharbage, Céline Teulière, Pierre Bouges et al. (+1 more)
Vision foundation models pretrained on web-scale data have recently shown strong transfer capabilities on many downstream tasks, but their effectiveness for industrial visual inspection remains unclear. Industrial data differ substantially from web-data and often require fine-grained dense prediction, raising the question of whether modern self-supervised pretraining can improve over the conventional transfer-learning paradigm based on supervised ImageNet initialization. In this work, we compare ConvNeXt backbones pretrained with supervised ImageNet classification or DINOv3
distillation, and relate them to the conventional ResNet-50 baseline. We evaluate semantic
segmentation, instance
segmentation, and object detection across four downstream
datasets spanning RGB surface-defect inspection and X-ray defect detection. We further study both frozen and fully finetuned adaptation regimes. Our results show that DINOv3 offers no clear advantage in frozen transfer, but provides a stronger initialization after full finetuning on RGB tasks, yielding faster convergence and better final performance. Under X-ray modality shift, however, supervised ImageNet pretraining remains more effective in both frozen and finetuned settings. Overall, our findings suggest that modern
vision foundation models are promising for supervised RGB industrial inspection, but their transferability is strongly conditioned by downstream adaptation and target modality.
Read the full abstract ▾
All authors Mehdi Gharbage, Céline Teulière, Pierre Bouges, Thierry Chateau
Computer Vision
One-Forcing: Towards Stable One-Step Autoregressive Video Generation
Jiaqi Feng, Justin Cui, Yuanhao Ban et al. (+1 more)
Recent advances in autoregressive
diffusion-based
video generation have substantially improved the quality of real-time
video synthesis. However, most existing methods still require multiple denoising steps, while reducing sampling to a single step often leads to severe quality degradation: trajectory-based consistency
distillation methods often produce
videos with weak dynamics, whereas DMD-based methods, such as Self-Forcing, tend to generate blurry frames. We attribute this limitation to the teacher trajectories exhibiting highly concentrated
curvature near the high-noise endpoint, which poses a fundamental
geometric challenge for one-step
distillation under the consistency
distillation framework. To address these limitations, we propose One-Forcing, a simple yet effective approach that augments the DMD objective with an auxiliary GAN loss for high-quality and efficient one-step
video generation. We further find that framewise autoregression stabilizes
adversarial training, enabling higher-quality generation with substantially fewer training iterations than chunkwise autoregression. Experiments on VBench show that One-Forcing achieves a total score of 83.76, establishing state-of-the-art performance among one-step causal
video generation methods while remaining competitive with strong multi-step approaches.
Read the full abstract ▾
All authors Jiaqi Feng, Justin Cui, Yuanhao Ban, Cho-Jui Hsieh
Computer Vision
Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
Bingtian Qiao, Yue Shi, Yingjie Zhou et al. (+3 more)
Real-world image super-resolution aims to recover high-quality images from complex and unknown real-world degradations. However, existing generative Real-ISR methods largely inherit the dense latent representations and quadratic-cost global modeling paradigm developed for high-resolution image synthesis, causing computation,
memory usage, and inference latency to scale unfavorably with resolution and thus limiting practical deployment. We argue that the key bottleneck lies not in insufficient restoration priors, but in excessive
token redundancy and costly
token interactions during high-resolution restoration. Motivated by this observation, we revisit Real-ISR from the perspectives of compact latent representation and linear-complexity modeling, and propose SANA-SR, an efficient one-step restoration framework. Specifically, SANA-SR employs a deep compression autoencoder with a 32x compression ratio to drastically reduce latent
tokens while preserving restoration-relevant structures and textures. On top of this compact latent space, we introduce a linear-
attention DiT with LoRA fine-tuning, enabling efficient high-resolution restoration with linear-complexity
token mixing. Extensive experiments on all
benchmark datasets demonstrate that SANA-SR achieves highly competitive and often superior quantitative performance against existing methods, while restoring clearer and more realistic textures. Moreover, after
pruning, the deployed model runs in 0.019s with 407.95G MACs and 344M parameters, highlighting its strong potential for practical mobile deployment.
Read the full abstract ▾
All authors Bingtian Qiao, Yue Shi, Yingjie Zhou, Yong Guo, Guangtao Zhai, Jiezhang Cao
Computer Vision · Cross-listed from cs.LG
Commutator-Induced Uncertainty in VAEs
Tahereh Dehdarirad, Michael Felsberg, Gabriel Eilertsen et al. (+1 more)
Variational autoencoders (VAEs) often struggle to represent non-commutative structure in learned latent spaces.
Symmetry-aware VAEs commonly address this issue by enforcing commutativity through algebraic regularization, which is appropriate for commutative transformation groups but can suppress meaningful non-commutative structure when it is intrinsic to the data. We argue that non-commutativity should instead be explicitly diagnosed and reflected in reconstruction behavior. We introduce a Lie Group VAE framework that combines
geometric and algebraic perspectives on uncertainty while separating discrete generative factors from continuous
geometric transformations. In a first phase, the model is trained without structural constraints while algebraic non-commutativity is measured through finite Baker-Campbell-Hausdorff deviations and decoder order sensitivity is measured through reconstruction order-swap tests. These diagnostics reveal a scale mismatch between latent non-commutativity and reconstruction behavior under unconstrained training. In a second phase, we introduce a deformation-stability constraint with a data-driven calibration constant that aligns decoder sensitivity with algebraic non-commutativity. We evaluate the framework on dSprites, 3DShapes, 3DCars, and CelebA against generic and
symmetry-aware baselines, including beta-VAE, CLG-VAE, and CFASL. Across synthetic
benchmarks, the method improves reconstruction quality and yields decoder-level behavior more consistent with latent non-commutative structure. Qualitative analyses show clearer order-dependent latent compositions and more stable reconstructions. On CelebA, the model yields more faithful reconstructions and factor-specific latent traversals than CFASL, while also exhibiting meaningful order-dependent interactions between learned latent directions.
Read the full abstract ▾
All authors Tahereh Dehdarirad, Michael Felsberg, Gabriel Eilertsen, Ziliang Xiong
Computer Vision
DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation
Jie Hu, Zixiang Gao, Yutong He et al. (+1 more)
Diffusion transformers have achieved remarkable success in high-quality
video generation, yet their reliance on spatiotemporal 3D full
attention incurs prohibitive computational cost due to the quadratic complexity of
attention. Block sparse
attention is a common approach to mitigate this by focusing computation on important regions. However,
attention maps in DiTs exhibit inherently dynamic and fine-grained sparsity, which causes existing block sparse
attention methods to degrade significantly in quality, especially at high sparsity ratios. In this paper, we revisit block sparse
attention and derive a theoretical lower bound on
attention recall to characterize the key factors governing its effectiveness. Guided by these insights, we propose DFSAttn, a training-free sparse
attention framework that enables dynamic, fine-grained sparsification efficiently. DFSAttn incorporates three core designs:
Hilbert curve-based
token reordering to achieve fine-grained sparsity while preserving efficient GPU execution, hierarchical block scoring for accurate block importance estimation, and sparse mask caching with adaptive ratios to balance accuracy and efficiency. Experimental results demonstrate that DFSAttn consistently outperforms prior methods under high sparsity, achieving up to 2.1$\times$ end-to-end speedup while maintaining high generation quality. Our code is open-sourced and available at https://github.com/jessica-hujie/DFSAttn.
Read the full abstract ▾
All authors Jie Hu, Zixiang Gao, Yutong He, Kun Yuan
Computer Vision
FAST-ME: Foundation-aware Adaptive Stopping for Motion Estimation for Efficient IoT Video Analysis
Kakia Panagidi and Stathes Hadjieftymiadis
In modern multimedia systems, efficient
video processing is critical, especially in resource-constrained environments such as IoT-based camera networks, autonomous platforms, and wireless sensor multimedia systems. A key bottleneck in
video compression and understanding is block motion estimation (ME), a process that remains computationally expensive despite the development of fast search techniques. This work introduces an Optimal Stopping Theory (OST)
algorithm for block motion estimation based on the assessment of spatiotemporal differences within and across
video frames. It also proposes a semantic-aware motion estimation framework that integrates Foundation Models (FMs) with the OST-based decision process. By leveraging pretrained visual models such as
Vision Transformers (ViT) and the Segment Anything Model (SAM), the framework extracts semantic
attention scores that indicate the importance of motion within specific spatial regions. These scores are fused with traditional distortion-based metrics, such as the Sum of Absolute Differences (SAD), to guide a hybrid stopping criterion that jointly considers motion magnitude and semantic relevance. The resulting adaptive
algorithm stops early in redundant regions while continuing the search in areas where motion is semantically significant. Experiments compare the proposed solution with widely used approaches from the literature on
benchmark and
multimodal video datasets. The proposed method achieves a significant reduction in computation with minimal accuracy loss and improved semantic coverage. The results highlight the benefits of bridging low-level motion analysis with high-level semantic
reasoning, offering a promising direction for efficient
multimodal video understanding in next-generation smart systems.
Read the full abstract ▾
Computer Vision · Cross-listed from cs.LG
Sample-wise Targeted Adversarial Attacks on Test-time Adaptation
Phuc Duc Nguyen and Quang Duc Nguyen
Test-time adaptation (TTA) mitigates distribution shifts by adapting models to unlabeled test inputs, but also exposes them to
adversarial manipulation. Existing class-wise targeted attacks remain suboptimal for stealthy exploitation in this setting: since TTA operates on batches, forcing a subset of samples toward a target label unintentionally pulls similar benign samples along, resulting in a conspicuously high frequency of the target label that is easy to detect. To capture a more realistic threat, we introduce a sample-wise targeted attack. Unlike prior approaches, the attacker aims to misclassify only inputs carrying an attacker-chosen trigger, while preserving a benign-like prediction distribution to evade detection. To achieve this, we propose a meta-learning-based attack with a novel priority-aware gradient
alignment strategy that explicitly prioritizes attack success. The strategy formulates the gradient update as an ellipsoidal trust-region problem, mitigating gradient conflict between the attack and stealth objectives, while providing theoretical guarantees for effective optimization of the attack objective in the presence of gradient misalignment. Extensive experiments on CIFAR-10-C, CIFAR-100-C, and ImageNet-C across TTA protocols demonstrate that our method achieves high targeted success rates while maintaining prediction behavior close to benign adaptation under multiple label-free stealth metrics, making it difficult to detect in unlabeled TTA deployment scenarios. Furthermore, we demonstrate that our attack shows strong robustness against existing defenses.
Read the full abstract ▾
Computer Vision · Cross-listed from cs.LG
What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
Eunwoo Heo, Kyeongkook Seo and Jaejun Yoo
The explosive growth of open-source model repositories has created a Model Jungle, where checkpoints are frequently shared without adequate documentation or metadata. While weight-space learning offers a pathway to identify and analyze these models directly from their parameters, processing full-scale weights is computationally prohibitive. Probing-based methods have emerged as a lightweight alternative, extracting permutation-equivariant representations via learnable probe vectors. However, existing probing methods are limited by a single-view design: they capture first-order structures but fail to encode the rich, higher-order correlation patterns inherent in row-column interactions. To bridge this gap, we introduce MVProbe, a multi-perspective probing framework that synthesizes first-order signals with interaction-aware (Gram-based) views. Our approach is theoretically grounded; we analyze the scaling laws of different probing orders to derive a principled standardization and fusion strategy that ensures balanced contributions from all branches. On the Model Jungle
benchmark, MVProbe consistently outperforms the state-of-the-art ProbeX across diverse architectures, including discriminative backbones (ResNet, SupViT, MAE, DINO) and large-scale generative LoRA adapters (Stable
Diffusion LoRA).
Read the full abstract ▾
Computer Vision
Online Hand Gesture Recognition Using 3D Convolutional Neural Networks
Yinghao Qin and Tijana Timotijevic
In human computer interaction, real-time detection and classification of dynamic hand gestures is challenging as: 1) the system must run in a real-time
video stream and there is no noticeable lag in response after performing a gesture; 2) there is a large difference in how people perform gestures, making recognition more difficult. In this paper, an online hand gesture recognition system is proposed, which is able to localize gestures in real-time
video stream and recognize what these gestures are. To improve the robustness of the system, the sliding window approach is used to refine results from multiple windows. All of the models in my project are trained on Jester database, achieving 98+% accuracy for detector and 90+% accuracy for classifier. For the overall performance of the system, the best group can respond within three seconds and reach 37.5% Levenshtein accuracy on the homemade
dataset. The project codes used in this work are publicly available.
Read the full abstract ▾
Computer Vision
RS2AD-LiDAR: End-to-End Autonomous Driving LiDAR Data Generation from Roadside Sensor Observations
Runyi Huang, Ni Ding, Ruidan Xing et al. (+3 more)
End-to-end autonomous driving solutions, which directly process
multimodal sensory data and output fine-grained control commands, have gradually become a mainstream direction with the development of autonomous driving technology. However, current methods in this category rely on single-vehicle data collection for model training and optimization, which suffers from high acquisition and annotation costs, scarcity of valuable scenarios, and data silos. To address these challenges, we propose RS2AD-
LiDAR, a novel framework for reconstructing and generating vehicle-mounted
LiDAR data from roadside sensor observations. Since no public
dataset currently provides highly overlapping perception coverage between roadside and vehicle-mounted
LiDAR sensors, which is essential for studying roadside-to-vehicle data generation, we constructed a dedicated
dataset named R2V-
LiDAR which is used solely for evaluation in this work. Specifically, our method transforms roadside
LiDAR point clouds into the vehicle-mounted
LiDAR coordinate system, and synthesizes high-fidelity vehicle-mounted data via virtual
LiDAR modeling and point cloud resampling techniques. To the best of our knowledge, this is the first approach to reconstruct vehicle-mounted
LiDAR data from roadside sensor inputs. Extensive experimental comparisons demonstrate the semantic similarity between the generated data and real data. Furthermore, object detection experiments show that incorporating the generated data into real data for model training improves both Bird's Eye View (BEV) and 3D detection accuracy, thereby validating the effectiveness of the proposed method.
Read the full abstract ▾
All authors Runyi Huang, Ni Ding, Ruidan Xing, Yuheng Shi, Lei He, Keqiang Li
Computer Vision
Joint Target-Less Intrinsic and Extrinsic Camera-LiDAR Calibration using Deep Point Correspondences
Simon Bultmann, Daniele Cattaneo and Abhinav Valada
Accurate camera-
LiDAR calibration is a prerequisite for robust multi-modal perception in robotics. Recent target-less approaches based on deep point correspondences achieve remarkable performance for extrinsic calibration but assume rectified images with known intrinsics. In this work, we overcome this limitation and present the first fully target-less pipeline that jointly estimates camera intrinsics (pinhole model with radial-tangential distortion) and camera-
LiDAR extrinsics with deep pixel-point correspondences. Our approach extends deep correspondence-based calibration by (i) automatic intrinsic initialization via structure-from-motion, (ii) generalizing camera-
LiDAR matching to raw images with unknown intrinsics including distortion, and (iii) tightly coupling correspondence estimation with joint nonlinear optimization over both intrinsics and extrinsics. We evaluate our method on the KITTI
dataset with unseen camera-
LiDAR pairs and demonstrate that joint calibration achieves improved extrinsic accuracy while additionally recovering accurate intrinsics.
Read the full abstract ▾
Computer Vision
VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
Junwen Tan, Jinglin Liang, Hongyuan Chen et al. (+1 more)
Though rectified flow models have achieved remarkable performance in image,
video, and 3D generation, their practical deployments are challenged by slow inference speeds. Prior acceleration methods reuse cached features from previous steps, which neglects the growing mismatch between static caches and the evolving input, leading to reduced output fidelity. This work proposes Velocity Decomposition and Estimation (VDE), a training-free acceleration method that shifts the paradigm from caching-and-reusing to decomposing-and-estimating. Specifically, VDE decomposes the model's velocity into components parallel and orthogonal to the input, exploiting their temporal predictability and directional stability for precise, input-adaptive estimation. To prevent error accumulation, it periodically anchors the model's state via full forward passes. Extensive experiments on image and
video generation tasks demonstrate that VDE achieves substantial acceleration with minimal loss in visual quality. Notably, VDE accelerates Flux by 3.22 times and achieves an LPIPS of 0.069 on Qwen-Image, outperforming the best baseline with a 52.2% reduction.
Read the full abstract ▾
All authors Junwen Tan, Jinglin Liang, Hongyuan Chen, Shuangping Huang
Computer Vision
Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization
Tianyu Wang, Junjie Wu, Jingquan Gao et al. (+1 more)
Temporal Action Localization (TAL) has been extensively studied in generic
video understanding, while fine-grained sports scenarios, such as professional badminton, remain underexplored due to their complex and subtle spatio-temporal dynamics. In this paper, we focus on fine-grained TAL in professional badminton
videos and introduce a new
benchmark dataset, Fine-Badminton, which consists of 31 matches with 29 fine-grained stroke categories, covering 2104 rallies and 27597 annotated actions. To effectively capture the intricate motion patterns in such scenarios, we propose a Decoupling Spatio-Temporal Adapter (DSTA), which enables efficient modeling of spatio-temporal features within a parameter-efficient framework. Specifically, DSTA decomposes motion representation into three parallel branches, capturing temporal dynamics as well as vertical and horizontal spatial variations. The design allows the model to better distinguish subtle differences among fine-grained actions. Extensive experiments on both the Fine-Badminton
dataset and the ShuttleSet
benchmark demonstrate that the proposed method achieves state-of-the-art performance while introducing only a marginal increase in computational and parameter cost. These results validate the effectiveness and efficiency of the proposed approach for fine-grained temporal action localization.
Read the full abstract ▾
All authors Tianyu Wang, Junjie Wu, Jingquan Gao, Shishuo Li
Computer Vision
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models
Zizhao Tong, Yeying Jin, Hongfeng Lai et al. (+11 more)
Interactive world models for first-person shooter (FPS) games must resolve high-frequency overlapping control signals at every frame without disrupting unaffected regions. Existing methods inject actions globally and train on single titles, failing under dense FPS inputs. We observe that FPS actions are spatially selective: discrete events such as firing or reloading affect only a localized region around the weapon (the scope), while continuous camera and movement signals govern stable surroundings. We propose SCOPE, which inserts a conditioning module into each
transformer block of a pretrained
video diffusion model. It reshapes features into per-pixel temporal sequences so that each position computes its action response from local visual content. This separates in-scope effects from out-of-scope generation without
segmentation labels. We also introduce CrossFPS, the first multi-game FPS
dataset with frame-aligned action telemetry. It comprises 69K clips from 7 titles with 10-DoF controller signals, curated to remove gameplay bias. The model learns general visual-to-action mappings rather than game-specific patterns, enabling zero-shot transfer to unseen scenes. Experiments confirm strong action responsiveness, precise scope separation, and effective cross-game generalization.
Read the full abstract ▾
All authors Zizhao Tong, Yeying Jin, Hongfeng Lai, Zeqing Wang, Zhaohu Xing, Kexu Cheng, Haoran Xu, Zhao Pu, Shangwen Zhu, Ruili Feng, Jian Zhao, Yan Zhang, Hao Tang, Ling Shao
Computer Vision
CHASD: Language Increment-Calibrated Contrastive Decoding against Hallucination in LVLMs
Xiaoyi Huang, Kejia Zhang and Zhiming Luo
Large
Vision-
Language Models have shown strong
multimodal reasoning capabilities, yet they remain susceptible to object
hallucinations when
language priors dominate insufficient or misaligned visual evidence. Training-free contrastive decoding methods mitigate this issue by comparing predictions from original and perturbed visual inputs, but existing approaches either apply global perturbations that may alter useful visual evidence or invoke an additional negative branch at every decoding step. In this paper, we observe that
hallucination risks are transient and
token-specific: visual
attention shifts across generated
tokens, while some functional
tokens are produced with high confidence and do not require contrastive calibration. Based on this observation, we propose Contrastive
Hallucination-Aware Step-wise Decoding (CHASD) for Large
Vision-
Language Models, an inference-time framework for "calibration on demand". CHASD uses an uncertainty-driven confidence gate to activate the contrastive branch only when the maximum probability of the next-
token is less than the threshold, and constructs the negative branch through
attention-guided localized perturbations of the currently salient visual
tokens. This design reduces unnecessary negative-branch forward passes while preserving the original distribution for high-confidence steps. Experiments on POPE, AMBER, MME, MMHal-Bench, and CHAIR show that CHASD improves
hallucination-related metrics over strong training-free baselines with competitive inference efficiency.
Read the full abstract ▾
Computer Vision
GFSR: Geometric Fidelity and Spatial Refinement for Reliable Lane Detection
Tiancheng Wang, Zhaolu Ding, Richeng Xu et al. (+5 more)
Lane detection stands as a crucial perception task in autonomous driving and advanced driver assistance systems. However, existing methods still degrade in complex real scenarios due to two major limitations. First, classification confidence only characterizes the categorical existence of lane priors and has no strong correlation with
geometric quality. If threshold filtering and NMS are conducted merely based on this confidence, the model tends to retain lane priors with high confidence while eliminating those with lower confidence but superior
geometric representation. Secondly, the regression modules in existing methods weaken correlations among sampling points, hindering fine-grained optimization of distant, high-
curvature and complex-
topology lanes and causing underfitting. To address these issues, we propose
Geometric Fidelity and Spatial Refinement (GFSR), a framework consisting of LaneIoU-guided Confidence Calibration (LCC) and Adaptive Gated Location Refinement (AGLR). Specifically, LCC adopts LaneIoU as soft supervision to explicitly estimate the
geometric fidelity of lane priors, which is further fused with classification confidence to construct the Collaborative Reliability Index (CRI). This index guides lane prior filtering, effectively retaining those with high classification confidence and favorable
geometric quality. Meanwhile, cooperating with regression heads in each refinement stage, AGLR predicts sampling point lateral offsets and adopts a gating mechanism to adaptively regulate correction magnitude, strengthen inter-point correlations and boost model adaptability as well as robustness toward complex lane scenarios. Extensive experiments on CULane and CurveLanes demonstrate that our GFSR achieves state-of-the-art performance on CULane, with F1_50 and F1_75 scores of 81.46% and 65.01%, and reaches 87.35% F1_50 on CurveLanes.
Read the full abstract ▾
All authors Tiancheng Wang, Zhaolu Ding, Richeng Xu, Tianhui Zheng, Hui Liu, Hanyu Xuan, Zhiliang Wu, Guanghui Yue
Computer Vision
Enhancing Blood Cells Classification using Hybrid Quantum Neural Networks
Guilherme Cruz, Nouhaila Innan, Alberto Marchisio et al. (+2 more)
Accurate classification of microscopic blood
cells is still a critical task in medical image analysis, where subtle variations and limited data can challenge conventional deep learning models. As such, we investigate in this work the potential of Hybrid
Quantum-Classical Neural Networks (HQNNs) to enhance feature representation and improve classification performance in this domain. We propose a modular architecture combining a pre-trained ResNet-50 backbone with a low-dimensional latent bottleneck and a variational
quantum circuit, enabling a direct comparison between
quantum-enhanced and purely classical transformation mechanisms. To isolate the contribution of the
quantum component, we evaluate three architectures: a HQNN model, a Classical Matched Model with an additional nonlinear transformation layer of comparable capacity, and a baseline model without an intermediate transformation stage. Experiments conducted on two publicly available blood
cell datasets, namely the Blood
Cell Images
dataset and the PBC
dataset, demonstrate that HQNNs consistently achieve superior or more balanced performance across evaluation metrics. In the Blood
Cell Images
Dataset, the proposed approach improves macro F1-score by up to 3.7% compared to classical baselines, while improving the F1-score from 98.54% to 98.69% in the more challenging 8-class scenario with near-saturated performance. Additional evaluation on IBM
quantum hardware shows that the model remains robust under noise, with only a modest performance degradation relative to simulated results. These results indicate that
quantum feature transformations can enhance discriminative representations, particularly in challenging classification scenarios, and highlight the practical potential of HQNN models for medical imaging tasks.
Read the full abstract ▾
All authors Guilherme Cruz, Nouhaila Innan, Alberto Marchisio, Gabriel Falcao, Muhammad Shafique
Computer Vision · Cross-listed from eess.IV
Efficient Learned Image Compression without Entropy Coding
Hao Cao, Wenqi Guo, Zhijin Qin et al. (+1 more)
Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However,
entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present
Entropy-Coding Free Learned Image Compression (EF-LIC), a multi-rate framework that generates compact representation by removing statistical and correlation redundancy with low coding latency. First, we introduce unconstrained vector quantization and prove that its index distribution approaches the maximum-
entropy bound, yielding minimal statistical redundancy. Second, we propose a context-conditioned autoregressive transform that directly reparameterizes the latents to reduce inter-dependency. Theoretical analysis shows that EF-LIC can remove correlation redundancy as effectively as typical LIC with
entropy coding, leading to comparable compression performance. Experiments show EF-LIC achieves up to 67.86% bitrate reduction over MS-ILLM on Kodak with LPIPS. Ablation studies further show EF-LIC matches the compression performance of its
entropy-coding based variant while achieving over $3\times$ faster encoding and $5\times$ faster decoding.
Read the full abstract ▾
All authors Hao Cao, Wenqi Guo, Zhijin Qin, Jungong Han
Computer Vision
General Hazard Detection
Stephanie Ng, CP Lim, SueJen Looi et al. (+5 more)
Hazard, as an abstract concept, is typically defined through cognitive-level logical
reasoning rather than concrete examples. In contrast, existing hazard detection systems rely on predefined hazard categories and require intensive collection of labelled examples within detection or classification architectures. This approach faces three fundamental challenges when addressing abstract safety concepts: (1) noisy and sparse training data, (2) dynamically evolving definitions that change across contexts and time, and (3) limited generalisation to unseen or novel scenarios. To address these limitations, we present the CompliVision
dataset, the first general-purpose hazard
dataset designed for rule-based compliance assessment, along with a baseline framework for hazard evaluation. Our key innovation is decoupling the hazard concept from image-based examples by expressing safety requirements through
language-based rules. We ground our approach in authoritative domain regulations and ISO standards to define diverse hazard concepts across multiple domains. The CompliVision
dataset comprises 3,006 images spanning traffic, construction, and warehouse environments, with each image annotated for compliance against specific safety rules, accompanied by natural
language explanations highlighting the supporting visual evidence. To achieve robust generalisation, we develop an active learning framework to more effectively guide and refine
vision-
language models in assessing hazard compliance. While state-of-the-art VLMs demonstrate strong capabilities, they struggle with the fine-grained, context-dependent interpretation required for accurate safety assessment. We proposed a general hazard detection framework to address this limitation which combines LLaVA-based visual
reasoning with with human-in-the-loop feedback.
Read the full abstract ▾
All authors Stephanie Ng, CP Lim, SueJen Looi, Hendrik Zurlinden, David Nguyen, Lei Wei, Saeid Nahavandi, Hailing Zhou
Computer Vision
Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition
Yerim So, Jiyeong Kim, Jiwon Yoon et al. (+1 more)
Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text
alignment, a process that obscures local patch information and fine-grained spatio-temporal cues. We propose Similarity Volume Aggregation (SimVA), a framework that constructs a dense 4D spatio-temporal similarity volume from patch-level visual-text similarities. SimVA constructs a spatio-temporal similarity volume over local
video tokens and action classes, and employs class sampling to ensure similarity aggregation scalable to large vocabularies. The similarity volume is refined by spatial aggregation, which contextualizes local similarity patterns to improve intra-frame consistency. Motion-aware modulation further injects inter-frame variation cues, highlighting dynamically changing regions. Mamba-based temporal aggregation then models the
evolution of class-conditioned similarity patterns across frames. By maintaining dense visual-text correspondence, SimVA effectively transfers CLIP to
video action recognition, achieving competitive performance across zero-shot, few-shot, and base-to-novel
benchmarks.
Read the full abstract ▾
All authors Yerim So, Jiyeong Kim, Jiwon Yoon, Dongbo Min
Computer Vision
LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images
Yilong Liu, Wanhua Li, Chen Zhu-Tian et al. (+1 more)
We present LangFlash, a feed-forward framework for 3D
Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enriched with
language-aligned semantic features from sparse unposed multi-view images. Unlike optimization-based 3D methods, LangFlash directly predicts the geometry and semantics in a single forward pass, enabling low-latency 3D reconstruction and
language-consistent scene understanding. To support large-scale training, we enriched the RealEstate10k
dataset with coherent and dense semantic information for 3D semantic supervision. Furthermore, we propose a sparse semantic encoding scheme that combines a global semantic dictionary with locally varying per-primitive weights, preserving high-level linguistic information, while reducing representation complexity. Experimental results show that LangFlash achieves superior novel view synthesis and semantic consistency compared with previous methods. This study establishes a new paradigm for pose-free,
language-grounded 3D scene reconstruction, advancing generalizable 3D
vision and
multimodal scene understanding. Demo is available at https://liylo.github.io/langflash.github.io/.
Read the full abstract ▾
All authors Yilong Liu, Wanhua Li, Chen Zhu-Tian, Hanspeter Pfister
Computer Vision · Cross-listed from eess.IV
Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring
Shaoqing Duan, Haofei Song, Xintian Mao et al. (+2 more)
Defocus deblurring in pathological microscopy remains challenging due to the spatially varying and locally discontinuous nature of optical blur induced by a position-dependent integral imaging process. Existing deep learning methods, constrained by shift-invariance assumptions and limited interpretability, are not well suited to such heterogeneous blur patterns. Neural operators provide a principled alternative by modeling defocus formation directly as an integral operator, offering a new perspective on defocus deblurring. However, most existing neural operator architectures for low-level
vision rely on globally parameterized kernels that assume smoothness and stationarity, limiting their ability to model heterogeneous and locally discontinuous blur patterns. To address this limitation, we propose the Discontinuous Galerkin Neural Operator (DGNO), which parameterizes the integral kernel using a discontinuous Galerkin formulation with element-local volume operators and interface numerical fluxes. DGNO provides a principled combination of locality, heterogeneity modeling, and global coherence while preserving the underlying physics of optical image formation. Extensive and insightful experiments demonstrate that DGNO surpasses state-of-the-arts, delivering sharper reconstructions, robust handling of spatially varying blur, and scalable high-resolution performance. The code will be released at https://github.com/DeepMed-Lab-ECNU/Single-Image-Deblur.
Read the full abstract ▾
All authors Shaoqing Duan, Haofei Song, Xintian Mao, Qingli Li, Yan Wang
Computer Vision
DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection
Jie Zhu, Girish Chandar Ganesan and Xiaoming Liu
Monocular metric depth estimation has achieved strong progress with large-scale training and universal-camera modeling, yet robust deployment across diverse camera settings, such as perspective, fisheye, and panoramic images, remains challenging. Existing methods typically rely on a single depth
estimator, overlooking that different models encode different camera assumptions and perform best under different input domains. In this paper, we show that depth experts exhibit strong sample-wise complementarity: model preference is highly correlated with camera geometry, and multi-model fusion brings the largest gains on difficult samples where individual experts are unreliable. Motivated by these observations, we propose \ours, a
vision-
language agent for adaptive
monocular depth estimation. DepthAgent treats existing depth models as frozen tools and learns to analyze scene and camera cues, invoke suitable experts through multi-turn tool utilization, and select or fuse their predictions for each input. To optimize such discrete decision-making toward dense
geometric quality, we design a multi-reward reinforcement fine-tuning scheme that jointly encourages valid tool execution, camera/scene analysis, expert-selection quality, and inference efficiency. Extensive experiments across perspective, fisheye, and panoramic
benchmarks show that \ours consistently outperforms individual experts, fixed model fusion, and different selection strategies, with strong improvements on challenging samples, highlighting the critical role of expert selection and fusion. The code and model will be released upon publication.
Read the full abstract ▾
Computer Vision
U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025
Duc-Nhuan Le, Hoang-Phuc Nguyen, Thanh-Duy Lam et al. (+2 more)
Retrieving events from large-scale
video datasets is challenging due to complex temporal, spatial, and
multimodal information. This paper presents U-CESE, our solution for the AI Challenge HCMC 2025, a Unified Clip-based Event Search Engine for
multimodal event
retrieval across diverse
video sources. Building on CESE, U-CESE integrates its three modules into a single cohesive framework, ensuring consistent processing and
retrieval across query types. A core component is the Unified Clipping
Algorithm, which merges separate clipping
algorithms into one efficient pipeline. To handle large-scale data, we propose DAKE, a lightweight, training-free keyframe extraction method using JPEG file size variations to identify significant scene changes. Finally, we introduce ReCap, a temporally consistent captioning framework inspired by Recurrent Neural Network, generating detailed and context-aware textual descriptions. Experiments show that U-CESE delivers robust, consistent, and efficient performance in large-scale
multimodal event
retrieval.
Read the full abstract ▾
All authors Duc-Nhuan Le, Hoang-Phuc Nguyen, Thanh-Duy Lam, Minh-Nhut Dang, Minh-Hoang Le
Computer Vision
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
Songlin Yang, Haobin Zhong, Ruilin Zhang et al. (+23 more)
The rapid
evolution of generative
video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic workflows. However, reliable evaluation has emerged as a critical bottleneck. Existing
benchmarks predominantly evaluate ”whether it is right” (basic
prompt-following) while fundamentally neglecting ”whether it is good” (cinematic quality, acting, and aesthetics). Furthermore, current automated metrics lack the domain-specific rigor required to provide trustworthy signals, creating a severe credibility gap between human aesthetic perception and machine scoring. To bridge this gap, we introduce EvalVerse, a comprehensive, pipeline-aware, and expert-calibrated evaluation framework. We treat
video generation assessment not merely as an engineering task, but as a core scientific problem: the systematic digitization of subjective cinematic expertise. First, we organize domain knowledge into an evaluation taxonomy aligned with the professional filmmaking workflow (pre-production, production, and post-production). Second, we distill human expert judgments into a curated
dataset with large-scale human annotations. Third, we inject this knowledge into
Vision-
Language Models (VLMs) through an expert-calibrated fine-tuning strategy, enabling the VLM to perform explicit Chain-of-Thought
reasoning. Compared to previous works, EvalVerse not only retains compatibility with foundational ”rightness” metrics, but also significantly expands the criteria to ”goodness” and broaden the task coverage to complex multi-shot sequencing and audio-visual integration. Consequently, by providing granular diagnostic signals, EvalVerse transcends a static leaderboard and establishes a fundamental infrastructure for future work, such as reward models and evaluator
agent.
Read the full abstract ▾
All authors Songlin Yang, Haobin Zhong, Ruilin Zhang, Xiaotong Zhao, Shuai Li, Kai Zheng, Xuyi Yang, Zhe Wang, Zhenchen Tang, Yang Li, Bohai Gu, Zhengwei Peng, Yidan Huang, Mengzhou Luo, Yihang Bo, Dalu Feng, Yujia Zhang, Juntao Ma, Ruiqi Wang, Lvmin Zhang, Yuwei Guo, Frank Guan, Maneesh Agrawala, Hongbo Fu, Alan Zhao, Anyi Rao
Computer Vision
ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
Xiyang Wang, Xinlin Wang, Tingguang Zhou et al. (+7 more)
Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal
reasoning and global trajectory consistency. Autoregressive (AR) models capture interaction-aware temporal dependencies via causal factorization, but their step-wise decoding leads to error accumulation and suboptimal global structure. In contrast,
diffusion models optimize trajectories globally but lack explicit causal constraints, making them unreliable in interactive and safety-critical scenarios. This dichotomy reveals a deeper issue: existing methods treat causal modeling and global optimization as separate paradigms, without a principled way to unify them within a single trajectory distribution. To address this, we propose ChainFlow-VLA, which unifies causal generation and global refinement within a unified probabilistic framework. We formulate planning as a mixture over AR-induced modes and learn
Vision-
Language Model (VLM)-conditioned residual distributions over these modes. An autoregressive generator (Chain) produces a discrete set of causal trajectory modes, followed by a
diffusion-based refiner (Flow) that leverages VLM hidden states as semantic priors to perform mode-conditioned correction in residual space while preserving causal structure. This straightforward conditioning seamlessly injects high-level scene understanding into fine-grained trajectory adjustments. Experiments demonstrate that ChainFlow-VLA achieves robust planning in ambiguous and long-tail scenarios, achieving a state-of-the-art score of 94.85 on the NAVSIM v1 leaderboard, matching human-level performance (94.8). Code will be available at https://github.com/AFARI-Research/ChainFlow-VLA.
Read the full abstract ▾
All authors Xiyang Wang, Xinlin Wang, Tingguang Zhou, Gong Chen, Xingtai Gui, Zhi Xu, Xiaolei Wu, Feiyang Tan, Hangning Zhou, Mu Yang
Computer Vision
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
Hongbo Wang, Huaibo Huang, Pin Wang et al. (+3 more)
Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalignment between isotropic objectives and the intrinsic natural image
manifold. While Direct Preference Optimization offers a path to
alignment, its reliance on spectrally flat Gaussian noise fails to distinguish authentic high-frequency details from
hallucinations. To bridge this
geometric gap, we propose ASASR, a theoretically grounded framework that recasts the generative flow into a Sobolev-induced Riemannian geometry by explicitly coloring the noise transition kernel to mirror natural spectral decay. Driving this
geometric alignment, we integrate a parametric adversary grounded in the Riesz Representation
Theorem, which synthesizes targeted negative samples equivalent to worst-case Sobolev gradients to direct optimization along the tangent space of plausible structural failures. Extensive evaluations demonstrate that ASASR outperforms leading generative baselines, particularly in preserving spectral consistency and structural fidelity, offering a robust solution that effectively mitigates artifacts.
Read the full abstract ▾
All authors Hongbo Wang, Huaibo Huang, Pin Wang, Jinhua Hao, Chao Zhou, Ran He
Computer Vision · Cross-listed from cs.RO
Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
Zixuan Hu, Xuantuo Huang, Yancheng Li et al. (+3 more)
Navigating under non-stationary environment shifts poses a critical challenge for a
Vision-and-
Language Navigation (VLN)
agent deployed in the wild. Yet, existing Test-Time Adaptation (TTA) methods for VLN largely treat online adaptation as transient, isolated updates, leading to catastrophic forgetting and negative transfer. To overcome these issues, we propose Inter-Domain BridgE with Historical Assets (IDEA), a novel TTA framework that transforms adaptation into the accumulation and composition of assets. Specifically, IDEA introduces soft
prompts optimized via a Fisher-guided weighting scheme to capture the transferable knowledge. These optimized
prompts are then augmented with domain coordinates to form a dynamic asset library. Leveraging this library, IDEA constructs a cross-domain bridge by projecting the target domain onto the convex hull of historical knowledge. These designs form a complementary loop: the evolving library underpins bridge construction, while the bridge provides superior initialization to accelerate asset optimization. Extensive experiments across REVERIE, R2R, and R2R-CE
benchmarks demonstrate the consistent superiority of IDEA over existing methods, showcasing its ability to enable training-free adaptation via asset sharing.
Read the full abstract ▾
All authors Zixuan Hu, Xuantuo Huang, Yancheng Li, Yichun Hu, Shengyong Xu, Ling-Yu Duan