Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Tuesday 28 October
Digital image processing involves the systematic handling of images using advanced computer algorithms, and has gained significant attention in both academic and practical fields. Image enhancement is a crucial preprocessing stage in the image-processing chain, improving image quality and emphasizing features. This makes subsequent tasks (segmentation, feature extraction, classification) more reliable. Image enhancement is essential for rice leaf analysis, aiding in disease detection, nutrient deficiency evaluation, and growth analysis. Denoising followed by contrast enhancement are the primary steps. Image filters, generally employed for denoising, transform or enhance visual characteristics like brightness, contrast, and sharpness, playing a crucial role in improving overall image quality and enabling the extraction of useful information. This work provides an extensive comparative study of well-known image-denoising methods combined with CLAHE (Contrast Limited Adaptive Histogram Equalization) for efficient denoising of rice leaf images. The experiments were performed on a rice leaf image dataset to ensure the data is relevant and representative. Results were examined using various metrics to comprehensively test enhancement methods. This approach provides a strong basis for assessing the effectiveness of methodologies in digital image processing and reveals insights useful for future adaptation in agricultural research and other domains.
Computer Vision · Cross-listed from eess.AS
See the Speaker: Crafting High-Resolution Talking Faces from Speech with Prior Guidance and Region Refinement
Unlike existing methods that rely on source images as appearance references and use source speech to generate motion, this work proposes a novel approach that directly extracts information from the speech, addressing key challenges in speech-to-talking face. Specifically, we first employ a speech-to-face portrait generation stage, utilizing a speech-conditioned diffusion model combined with statistical facial prior and a sample-adaptive weighting module to achieve high-quality portrait generation. In the subsequent speech-driven talking face generation stage, we embed expressive dynamics such as lip movement, facial expressions, and eye movements into the latent space of the diffusion model and further optimize lip synchronization using a region-enhancement module. To generate high-resolution outputs, we integrate a pre-trained Transformer-based discrete codebook with an image rendering network, enhancing video frame details in an end-to-end manner. Experimental results demonstrate that our method outperforms existing approaches on the HDTF, VoxCeleb, and AVSpeech datasets. Notably, this is the first method capable of generating high-resolution, high-quality talking face videos exclusively from a single speech input.
Read the full abstract
Computer Vision
Efficient License Plate Recognition via Pseudo-Labeled Supervision with Grounding DINO and YOLOv8
Developing a highly accurate automatic license plate recognition system (ALPR) is challenging due to environmental factors such as lighting, rain, and dust. Additional difficulties include high vehicle speeds, varying camera angles, and low-quality or low-resolution images. ALPR is vital in traffic control, parking, vehicle tracking, toll collection, and law enforcement applications. This paper proposes a deep learning strategy using YOLOv8 for license plate detection and recognition tasks. This method seeks to enhance the performance of the model using datasets from Ontario, Quebec, California, and New York State. It achieved an impressive recall rate of 94% on the dataset from the Center for Pattern Recognition and Machine Intelligence (CENPARMI) and 91% on the UFPR-ALPR dataset. In addition, our method follows a semi-supervised learning framework, combining a small set of manually labeled data with pseudo-labels generated by Grounding DINO to train our detection model. Grounding DINO, a powerful vision-language model, automatically annotates many images with bounding boxes for license plates, thereby minimizing the reliance on labor-intensive manual labeling. By integrating human-verified and model-generated annotations, we can scale our dataset efficiently while maintaining label quality, which significantly enhances the training process and overall model performance. Furthermore, it reports character error rates for both datasets, providing additional insight into system performance.
Read the full abstract
Computer Vision · Cross-listed from cs.IT
Resi-VidTok: An Efficient and Decomposed Progressive Tokenization Framework for Ultra-Low-Rate and Lightweight Video Transmission
Real-time transmission of video over wireless networks remains highly challenging, even with advanced deep models, particularly under severe channel conditions such as limited bandwidth and weak connectivity. In this paper, we propose Resi-VidTok, a Resilient Tokenization-Enabled framework designed for ultra-low-rate and lightweight video transmission that delivers strong robustness while preserving perceptual and semantic fidelity on commodity digital hardware. By reorganizing spatio–temporal content into a discrete, importance-ordered token stream composed of key tokens and refinement tokens, Resi-VidTok enables progressive encoding, prefix-decodable reconstruction, and graceful quality degradation under constrained channels. A key contribution is a resilient 1D tokenization pipeline for video that integrates differential temporal token coding, explicitly supporting reliable recovery from incomplete token sets using a single shared framewise decoder–without auxiliary temporal extractors or heavy generative models. Furthermore, stride-controlled frame sparsification combined with a lightweight decoder-side interpolator reduces transmission load while maintaining motion continuity. Finally, a channel-adaptive source–channel coding and modulation scheme dynamically allocates rate and protection according to token importance and channel condition, yielding stable quality across adverse SNRs. Evaluation results indicate robust visual and semantic consistency at channel bandwidth ratios (CBR) as low as 0.0004 and real-time reconstruction at over 30 fps, demonstrating the practicality of Resi-VidTok for energy-efficient, latency-sensitive, and reliability-critical wireless applications.
Read the full abstract
Computer Vision
FT-ARM: Fine-Tuned Agentic Reflection Multimodal Language Model for Pressure Ulcer Severity Classification with Reasoning
Pressure ulcers (PUs) are a serious and prevalent healthcare concern. Accurate classification of PU severity (Stages I-IV) is essential for proper treatment but remains challenging due to subtle visual distinctions and subjective interpretation, leading to variability among clinicians. Prior AI-based approaches using Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) achieved promising accuracy but offered limited interpretability. We present FT-ARM (Fine-Tuned Agentic Reflection Multimodal model), a fine-tuned multimodal large language model (MLLM) with an agentic self-reflection mechanism for pressure ulcer severity classification. Inspired by clinician-style diagnostic reassessment, FT-ARM iteratively refines its predictions by reasoning over visual features and encoded clinical knowledge from text, enhancing both accuracy and consistency. On the publicly available Pressure Injury Image Dataset (PIID), FT-ARM, fine-tuned from LLaMA 3.2 90B, achieved 85% accuracy in classifying PU stages I-IV, surpassing prior CNN-based models by +4%. Unlike earlier CNN/ViT studies that relied solely on offline evaluations, FT-ARM is designed and tested for live inference, reflecting real-time deployment conditions. Furthermore, it produces clinically grounded natural-language explanations, improving interpretability and trust. By integrating fine-tuning and reflective reasoning across multimodal inputs, FT-ARM advances the reliability, transparency, and clinical applicability of automated wound assessment systems, addressing the critical need for consistent and explainable PU staging to support improved patient care.
Read the full abstract
Computer Vision · Cross-listed from cs.RO
SCOUT: A Lightweight Framework for Scenario Coverage Assessment in Autonomous Driving
Assessing scenario coverage is crucial for evaluating the robustness of autonomous agents, yet existing methods rely on expensive human annotations or computationally intensive Large Vision-Language Models (LVLMs). These approaches are impractical for large-scale deployment due to cost and efficiency constraints. To address these shortcomings, we propose SCOUT (Scenario Coverage Oversight and Understanding Tool), a lightweight surrogate model designed to predict scenario coverage labels directly from an agent's latent sensor representations. SCOUT is trained through a distillation process, learning to approximate LVLM-generated coverage labels while eliminating the need for continuous LVLM inference or human annotation. By leveraging precomputed perception features, SCOUT avoids redundant computations and enables fast, scalable scenario coverage estimation. We evaluate our method across a large dataset of real-life autonomous navigation scenarios, demonstrating that it maintains high accuracy while significantly reducing computational cost. Our results show that SCOUT provides an effective and practical alternative for large-scale coverage analysis. While its performance depends on the quality of LVLM-generated training labels, SCOUT represents a major step toward efficient scenario coverage oversight in autonomous systems.
Read the full abstract
Computer Vision
IBIS: A Hybrid Inception-BiLSTM and SVM Ensemble for Robust Doppler-based Human Activity Recognition
Wi-Fi sensing is a leading technology for Human Activity Recognition (HAR), offering a non-intrusive and cost-effective solution for healthcare and smart environments. Despite its potential, existing methods struggle with domain shift issues, often failing to generalize to unseen environments due to overfitting. This paper proposes IBIS, a robust ensemble framework combining Inception-Bidirectional Long Short-Term Memory (BiLSTM) for feature extraction and Support Vector Machine (SVM) for classification of Doppler signatures. The proposed architecture specifically targets generalization capabilities. Experimental results on multiple datasets show that IBIS achieves 95.40% accuracy, delivering a 7.58% performance gain compared to standard architectures in cross-scenario evaluations on external datasets. The analysis confirms that IBIS effectively mitigates environmental dependency in Wi-Fi-based HAR.
Read the full abstract
Computer Vision
Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
In multimodal learning, dominant modalities often overshadow others, limiting generalization. We propose Modality-Aware Sharpness-Aware Minimization (M-SAM), a model-agnostic framework that applies to many modalities and supports early and late fusion scenarios. In every iteration, M-SAM in three steps optimizes learning. First, it identifies the dominant modality based on modalities' contribution in the accuracy using Shapley. Second, it decomposes the loss landscape, or in another language, it modulates the loss to prioritize the robustness of the model in favor of the dominant modality, and third, M-SAM updates the weights by backpropagation of modulated gradients. This ensures robust learning for the dominant modality while enhancing contributions from others, allowing the model to explore and exploit complementary features that strengthen overall performance. Extensive experiments on four diverse datasets show that M-SAM outperforms the latest state-of-the-art optimization and gradient manipulation methods and significantly balances and improves multimodal learning.
Read the full abstract
Computer Vision
Understanding Multi-View Transformers
Multi-view transformers such as DUSt3R are revolutionizing 3D vision by solving 3D tasks in a feed-forward manner. However, contrary to previous optimization-based pipelines, the inner mechanisms of multi-view transformers are unclear. Their black-box nature makes further improvements beyond data scaling challenging and complicates usage in safety- and reliability-critical applications. Here, we present an approach for probing and visualizing 3D representations from the residual connections of the multi-view transformers' layers. In this manner, we investigate a variant of the DUSt3R model, shedding light on the development of its latent state across blocks, the role of the individual layers, and suggest how it differs from methods with stronger inductive biases of explicit global pose. Finally, we show that the investigated variant of DUSt3R estimates correspondences that are refined with reconstructed geometry. The code used for the analysis is available at https://github.com/JulienGaubil/und3rstand .
Read the full abstract
Computer Vision
VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos
Although recent video generative models are getting more capable of following external camera controls, imposed by either text descriptions or camera trajectories, they still struggle to generalize to unconventional camera motions, which is crucial in creating truly original and artistic videos. The challenge lies in finding sufficient training videos with the intended uncommon camera motions. To this end, we propose VividCam, a training paradigm that enables diffusion models to learn complex camera motions from synthetic videos, releasing the reliance on collecting realistic training videos. VividCam incorporates multiple disentanglement strategies that isolate camera motion learning from synthetic appearance artifacts, ensuring more robust motion representation and mitigating domain shift. We show that our design synthesizes a wide range of precisely controlled camera motions using surprisingly simple synthetic data. Notably, this synthetic data often consists of basic geometries within a low-poly 3D scene and can be efficiently rendered by engines like Unity. Our video results can be found in https://wuqiuche.github.io/VividCamDemoPage/ .
Read the full abstract
Computer Vision
Pixels to Signals: A Real-Time Framework for Traffic Demand Estimation
Traffic congestion is becoming a challenge in the rapidly growing urban cities, resulting in increasing delays and inefficiencies within urban transportation systems. To address this issue a comprehensive methodology is designed to optimize traffic flow and minimize delays. The framework is structured with three primary components: (a) vehicle detection, (b) traffic prediction, and (c) traffic signal optimization. This paper presents the first component, vehicle detection. The methodology involves analyzing multiple sequential frames from a camera feed to compute the background, i.e. the underlying roadway, by averaging pixel values over time. The computed background is then utilized to extract the foreground, where the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is applied to detect vehicles. With its computational efficiency and minimal infrastructure modification requirements, the proposed methodology offers a practical and scalable solution for real-world deployment.
Read the full abstract
Computer Vision
Proper Body Landmark Subset Enables More Accurate and 5X Faster Recognition of Isolated Signs in LIBRAS
This paper examines the feasibility of utilizing lightweight body landmark detection for recognizing isolated signs in Brazilian Sign Language (LIBRAS). Although the use of skeleton-image representation has enabled substantial improvements in recognition performance, the use of OpenPose for landmark extraction hindered time performance. In a preliminary investigation, we observed that simply replacing OpenPose with lightweight MediaPipe, while improving processing speed, significantly reduced accuracy. To overcome this limitation, we explored landmark subset selection strategies to optimize recognition performance. Experimental results show that a proper landmark subset achieves comparable or superior performance to state-of-the-art methods while reducing processing time by more than 5X. As an additional contribution, we demonstrate that spline-based imputation effectively mitigates missing landmark issues, leading to substantial accuracy gains.
Read the full abstract
Computer Vision
FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables
Maturity estimation of fruits and vegetables is a critical task for agricultural automation, directly impacting yield prediction and robotic harvesting. Current deep learning approaches predominantly treat maturity as a discrete classification problem (e.g., unripe, ripe, overripe). This rigid formulation, however, fundamentally conflicts with the continuous nature of the biological ripening process, leading to information loss and ambiguous class boundaries. In this paper, we challenge this paradigm by reframing maturity estimation as a continuous, probabilistic learning task. We propose a novel architectural modification to the state-of-the-art, real-time object detector, RT-DETRv2, by introducing a dedicated probabilistic head. This head enables the model to predict a continuous distribution over the maturity spectrum for each detected object, simultaneously learning the mean maturity state and its associated uncertainty. This uncertainty measure is crucial for downstream decision-making in robotics, providing a confidence score for tasks like selective harvesting. Our model not only provides a far richer and more biologically plausible representation of plant maturity but also maintains exceptional detection performance, achieving a mean Average Precision (mAP) of 85.6% on a challenging, large-scale fruit dataset. We demonstrate through extensive experiments that our probabilistic approach offers more granular and accurate maturity assessments than its classification-based counterparts, paving the way for more intelligent, uncertainty-aware automated systems in modern agriculture
Read the full abstract
Computer Vision · Cross-listed from cs.CL
Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation
We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a more prevalent source of information online, RAG systems must integrate such media into generation. Yet, existing evaluation methods for RAG are largely text-centric and do not readily transfer to multimodal settings. MiRAGE is a claim-centric approach to multimodal RAG evaluation, consisting of InfoF1, which assesses factuality and information coverage, and CiteF1, which assesses citation support and completeness. We show that, when applied by humans, MiRAGE strongly aligns with extrinsic judgments of output quality. We additionally introduce an automatic implementation of MiRAGE and compare it to multimodal variants of three prominent text-centric RAG metrics—ALCE, ARGUE, and RAGAS—finding that MiRAGE outperforms all three on text while being the only one to generalize to multimodal sources. We release open-source implementations and outline evaluation methods for multimodal RAG.
Read the full abstract
Computer Vision
The Generation Phases of Flow Matching: a Denoising Perspective
Flow matching has achieved remarkable success, yet the factors influencing the quality of its generation process remain poorly understood. In this work, we adopt a denoising perspective and design a framework to empirically probe the generation process. Laying down the formal connections between flow matching models and denoisers, we provide a common ground to compare their performances on generation and denoising. This enables the design of principled and controlled perturbations to influence sample generation: noise and drift. This leads to new insights on the distinct dynamical phases of the generative process, enabling us to precisely characterize at which stage of the generative process denoisers succeed or fail and why this matters.
Read the full abstract
Computer Vision
MCIHN: A Hybrid Network Model Based on Multi-path Cross-modal Interaction for Multimodal Emotion Recognition
Multimodal emotion recognition is crucial for future human-computer interaction. However, accurate emotion recognition still faces significant challenges due to differences between different modalities and the difficulty of characterizing unimodal emotional information. To solve these problems, a hybrid network model based on multipath cross-modal interaction (MCIHN) is proposed. First, adversarial autoencoders (AAE) are constructed separately for each modality. The AAE learns discriminative emotion features and reconstructs the features through a decoder to obtain more discriminative information about the emotion classes. Then, the latent codes from the AAE of different modalities are fed into a predefined Cross-modal Gate Mechanism model (CGMM) to reduce the discrepancy between modalities, establish the emotional relationship between interacting modalities, and generate the interaction features between different modalities. Multimodal fusion using the Feature Fusion module (FFM) for better emotion recognition. Experiments were conducted on publicly available SIMS and MOSI datasets, demonstrating that MCIHN achieves superior performance.
Read the full abstract
Computer Vision
Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which only 6.1 billion are active per token. This architecture enables highly efficient scaling (dramatically improving computational efficiency while significantly expanding model capacity) and empowers stronger unified multimodal intelligence across vision, speech, and language, representing a key step toward Artificial General Intelligence (AGI). Compared to its predecessor, the upgraded version exhibits substantial improvements across multimodal understanding and generation. Notably, it achieves strong performance on vision-language understanding benchmarks, with overall scores on par with Gemini 2.5 Pro, and enables seamless switching among multimodal tasks in multi-turn interactions. In speech, it achieves strong performance in contextual and dialect-aware ASR while enabling joint, continuous-generation of speech, sound, and music. In vision, it introduces generative semantic segmentation that achieves competitive standalone performance and enhances spatial control and editing consistency, alongside marked improvements in identity preservation, and high-fidelity in-image text rendering. Together, these capabilities demonstrate that a single unified model can serve as a practical foundation for general-purpose multimodal intelligence.
Read the full abstract
Computer Vision
SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing
With the rapid advancement of text-to-image (T2I) models, ensuring their safety has become increasingly critical. Existing safety approaches can be categorized into training-time and inference-time methods. While inference-time methods are widely adopted due to their cost-effectiveness, they often suffer from limitations such as over-refusal and imbalance between safety and utility. To address these challenges, we propose a multi-round safety editing framework that functions as a model-agnostic, plug-and-play module, enabling efficient safety alignment for any text-to-image model. Central to this framework is MR-SafeEdit, a multi-round image-text interleaved dataset specifically constructed for safety editing in text-to-image generation. We introduce a post-hoc safety editing paradigm that mirrors the human cognitive process of identifying and refining unsafe content. To instantiate this paradigm, we develop SafeEditor, a unified MLLM capable of multi-round safety editing on generated images. Experimental results show that SafeEditor surpasses prior safety approaches by reducing over-refusal while achieving a more favorable safety-utility balance.
Read the full abstract
Computer Vision
Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection
The advent of multi-modal large language models (MLLMs) has greatly advanced research on video fake news detection (VFND) tasks. Existing benchmarks typically focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process. To address these limitations, we introduce {POVFNDB (Process-oriented Video Fake News Detection Benchmark)}, a process-oriented benchmark comprising 10 tasks designed to systematically evaluate MLLMs' perception, understanding, and reasoning capabilities in VFND. This benchmark contains 36,240 human-annotated question-answer (QA) in structured or open-ended formats, spanning 15 distinct evaluation dimensions that characterize different aspects of the video fake news detection process. Using POVFNDB, we conduct comprehensive evaluations on both proprietary and open-source MLLMs. Moreover, we establish a strong benchmark baseline by fine-tuning Qwen2.5VL-7B-Instruct on process-oriented chain-of-thought data constructed with our proposed POVFND-CoT framework, achieving state-of-the-art performance on VFND.
Read the full abstract
Computer Vision
Deep Feature Optimization for Enhanced Fish Freshness Assessment
Assessing fish freshness is vital for ensuring food safety and minimizing economic losses in the seafood industry. However, traditional sensory evaluation remains subjective, time-consuming, and inconsistent. Although recent advances in deep learning have automated visual freshness prediction, challenges related to accuracy and feature transparency persist. This study introduces a unified three-stage framework that refines and leverages deep visual representations for reliable fish freshness assessment. First, five state-of-the-art vision architectures - ResNet-50, DenseNet-121, EfficientNet-B0, ConvNeXt-Base, and Swin-Tiny - are fine-tuned to establish a strong baseline. Next, multi-level deep features extracted from these backbones are used to train seven classical machine learning classifiers, integrating deep and traditional decision mechanisms. Finally, feature selection methods based on Light Gradient Boosting Machine (LGBM), Random Forest, and Lasso identify a compact and informative subset of features. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate that the best configuration combining Swin-Tiny features, an Extra Trees classifier, and LGBM-based feature selection achieves an accuracy of 85.99%, outperforming recent studies on the same dataset by 8.69-22.78%. These findings confirm the effectiveness and generalizability of the proposed framework for visual quality evaluation tasks.
Read the full abstract
Computer Vision
DualCap: Enhancing Lightweight Image Captioning via Dual Retrieval with Similar Scenes Visual Prompts
Recent lightweight retrieval-augmented image caption models often utilize retrieved data solely as text prompts, thereby creating a semantic gap by leaving the original visual features unenhanced, particularly for object details or complex scenes. To address this limitation, we propose $DualCap$, a novel approach that enriches the visual representation by generating a visual prompt from retrieved similar images. Our model employs a dual retrieval mechanism, using standard image-to-text retrieval for text prompts and a novel image-to-image retrieval to source visually analogous scenes. Specifically, salient keywords and phrases are derived from the captions of visually similar scenes to capture key objects and similar details. These textual features are then encoded and integrated with the original image features through a lightweight, trainable feature fusion network. Extensive experiments demonstrate that our method achieves competitive performance while requiring fewer trainable parameters compared to previous visual-prompting captioning approaches.
Read the full abstract
Computer Vision · Cross-listed from q-bio.QM
CT-Less Attenuation Correction Using Multiview Ensemble Conditional Diffusion Model on High-Resolution Uncorrected PET Images
Accurate quantification in positron emission tomography (PET) is essential for accurate diagnostic results and effective treatment tracking. A major issue encountered in PET imaging is attenuation. Attenuation refers to the diminution of photon detected as they traverse biological tissues before reaching detectors. When such corrections are absent or inadequate, this signal degradation can introduce inaccurate quantification, making it difficult to differentiate benign from malignant conditions, and can potentially lead to misdiagnosis. Typically, this correction is done with co-computed Computed Tomography (CT) imaging to obtain structural data for calculating photon attenuation across the body. However, this methodology subjects patients to extra ionizing radiation exposure, suffers from potential spatial misregistration between PET/CT imaging sequences, and demands costly equipment infrastructure. Emerging advances in neural network architectures present an alternative approach via synthetic CT image synthesis. Our investigation reveals that Conditional Denoising Diffusion Probabilistic Models (DDPMs) can generate high quality CT images from non attenuation corrected PET images in order to correct attenuation. By utilizing all three orthogonal views from non-attenuation-corrected PET images, the DDPM approach combined with ensemble voting generates higher quality pseudo-CT images with reduced artifacts and improved slice-to-slice consistency. Results from a study of 159 head scans acquired with the Siemens Biograph Vision PET/CT scanner demonstrate both qualitative and quantitative improvements in pseudo-CT generation. The method achieved a mean absolute error of 32 $\pm$ 10.4 HU on the CT images and an average error of (1.48 $\pm$ 0.68)% across all regions of interest when comparing PET images reconstructed using the attenuation map of the generated pseudo-CT versus the true CT.
Read the full abstract
Computer Vision
Conflict Adaptation in Vision-Language Models
A signature of human cognitive control is conflict adaptation: improved performance on a high-conflict trial following another high-conflict trial. This phenomenon offers an account for how cognitive control, a scarce resource, is recruited. Using a sequential Stroop task, we find that 12 of 13 vision-language models (VLMs) tested exhibit behavior consistent with conflict adaptation, with the lone exception likely reflecting a ceiling effect. To understand the representational basis of this behavior, we use sparse autoencoders (SAEs) to identify task-relevant supernodes in InternVL 3.5 4B. Partially overlapping supernodes emerge for text and color in both early and late layers, and their relative sizes mirror the automaticity asymmetry between reading and color naming in humans. We further isolate a conflict-modulated supernode in layers 24-25 whose ablation significantly increases Stroop errors while minimally affecting congruent trials.
Read the full abstract
Computer Vision
Generative View Stitching
Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided video generation with a predefined camera trajectory, this limitation leads to collisions with the generated scene, after which autoregression quickly collapses. To address this, we propose Generative View Stitching (GVS), which samples the entire sequence in parallel such that the generated scene is faithful to every part of the predefined camera trajectory. Our main contribution is a sampling algorithm that extends prior work on diffusion stitching for robot planning to video generation. While such stitching methods usually require a specially trained model, GVS is compatible with any off-the-shelf video model trained with Diffusion Forcing, a prevalent sequence diffusion framework that we show already provides the affordances necessary for stitching. We then introduce Omni Guidance, a technique that enhances the temporal consistency in stitching by conditioning on both the past and future, and that enables our proposed loop-closing mechanism for delivering long-range coherence. Overall, GVS achieves camera-guided video generation that is stable, collision-free, frame-to-frame consistent, and closes loops for a variety of predefined camera paths, including Oscar Reutersvärd's Impossible Staircase. Results are best viewed as videos at https://andrewsonga.github.io/gvs.
Read the full abstract
Computer Vision
Uniform Discrete Diffusion with Metric Path for Video Generation
Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-context inconsistency. In this work, we revisit discrete generative modeling and present Uniform discRete diffuSion with metric pAth (URSA), a simple yet powerful framework that bridges the gap with continuous approaches for the scalable video generation. At its core, URSA formulates the video generation task as an iterative global refinement of discrete spatiotemporal tokens. It integrates two key designs: a Linearized Metric Path and a Resolution-dependent Timestep Shifting mechanism. These designs enable URSA to scale efficiently to high-resolution image synthesis and long-duration video generation, while requiring significantly fewer inference steps. Additionally, we introduce an asynchronous temporal fine-tuning strategy that unifies versatile tasks within a single model, including interpolation and image-to-video generation. Extensive experiments on challenging video and image generation benchmarks demonstrate that URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods. Code and models are available at https://github.com/baaivision/URSA
Read the full abstract
Computer Vision
Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language models (LLMs), existing attempts to apply MoE to Diffusion Transformers (DiTs) have yielded limited gains. We attribute this gap to fundamental differences between language and visual tokens. Language tokens are semantically dense with pronounced inter-token variation, while visual tokens exhibit spatial redundancy and functional heterogeneity, hindering expert specialization in vision MoE. To this end, we present ProMoE, an MoE framework featuring a two-step router with explicit routing guidance that promotes expert specialization. Specifically, this guidance encourages the router to partition image tokens into conditional and unconditional sets via conditional routing according to their functional roles, and refine the assignments of conditional image tokens through prototypical routing with learnable prototypes based on semantic content. Moreover, the similarity-based expert allocation in latent space enabled by prototypical routing offers a natural mechanism for incorporating explicit semantic guidance, and we validate that such guidance is crucial for vision MoE. Building on this, we propose a routing contrastive loss that explicitly enhances the prototypical routing process, promoting intra-expert coherence and inter-expert diversity. Extensive experiments on ImageNet benchmark demonstrate that ProMoE surpasses state-of-the-art methods under both Rectified Flow and DDPM training objectives. Code is available at https://github.com/ali-vilab/ProMoE.
Read the full abstract
Computer Vision
Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?
Object binding, the brain's ability to bind the many features that collectively represent an object into a coherent whole, is central to human cognition. It groups low-level perceptual features into high-level object representations, stores those objects efficiently and compositionally in memory, and supports human reasoning about individual object instances. While prior work often imposes object-centric attention (e.g., Slot Attention) explicitly to probe these benefits, it remains unclear whether this ability naturally emerges in pre-trained Vision Transformers (ViTs). Intuitively, they could: recognizing which patches belong to the same object should be useful for downstream prediction and thus guide attention. Motivated by the quadratic nature of self-attention, we hypothesize that ViTs represent whether two patches belong to the same object, a property we term IsSameObject. We decode IsSameObject from patch embeddings across ViT layers using a quadratic similarity probe, which reaches over 90% accuracy. Crucially, this object-binding capability emerges reliably in DINO, CLIP, and ImageNet-supervised ViTs, but is markedly weaker in MAE, suggesting that binding is not a trivial architectural artifact, but an ability acquired through specific pretraining objectives. We further discover that IsSameObject is encoded in a low-dimensional subspace on top of object features, and that this signal actively guides attention. Ablating IsSameObject from model activations degrades downstream performance and works against the learning objective, implying that emergent object binding naturally serves the pretraining objective. Our findings challenge the view that ViTs lack object binding and highlight how symbolic knowledge of "which parts belong together" emerges naturally in a connectionist system.
Read the full abstract
Computer Vision
MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detection
Infrastructure-based perception plays a crucial role in intelligent transportation systems by providing global situational awareness and enabling cooperative autonomy. However, camera-based 3D object detection remains challenging under multi-view infrastructure setups, heterogeneous camera configurations, degraded sensing conditions, diverse road layouts, and adverse environmental conditions. We introduce MIC-BEV, a Transformer-based bird's-eye-view (BEV) perception framework for infrastructure-based multi-camera 3D object detection. MIC-BEV supports a variable number of cameras with heterogeneous intrinsic and extrinsic parameters and uses a graph-enhanced fusion module to adaptively integrate multi-view image features by modeling geometric relationships between cameras and the BEV grid. To support training and evaluation, we introduce M2I, a synthetic dataset featuring diverse camera layouts, road geometries, environmental conditions, and sensor-degradation cases. Experiments on the simulated M2I dataset and the real-world RoScenes dataset show that MIC-BEV achieves strong 3D detection performance and improved robustness under challenging conditions. Ablation studies validate the effectiveness of its key design choices, while weight analyses show that the learned fusion weights are associated with view-reliability factors and adapt to degraded camera inputs. We further report computational cost and deployment-related factors, providing additional evidence of practical feasibility and real-world deployment potential. These results indicate that MIC-BEV is a promising framework for infrastructure-based perception. The dataset and source code are available at: https://github.com/HandsomeYun/MIC-BEV.
Read the full abstract
Computer Vision
SAGE: Structure-Aware Generative Video Transitions between Diverse Clips
Video transitions aim to synthesize intermediate frames between two clips, but naive approaches such as linear blending introduce artifacts that limit professional use or break temporal coherence. Traditional techniques (cross-fades, morphing, frame interpolation) and recent generative inbetweening methods can produce high-quality plausible intermediates, but they struggle with bridging diverse clips involving large temporal gaps or significant semantic differences, leaving a gap for content-aware and visually coherent transitions. We address this challenge by drawing on artistic workflows, distilling strategies such as aligning silhouettes and interpolating salient features to preserve structure and perceptual continuity. Building on these strategies, we propose SAGE (Structure-Aware Generative vidEo transitions) as a simple yet effective zeroshot approach that combines structural guidance, provided via line maps and motion flow, with generative synthesis, enabling smooth, motion-consistent transitions without fine-tuning. Extensive experiments and comparison with current alternatives, namely [FILM, TVG, DiffMorpher, VACE, GI], demonstrate that SAGE outperforms both classical and the latest generative baselines on quantitative metrics and user studies for producing transitions between diverse clips. The simple method effectively bypasses the need to acquire suitable training data, which is particularly difficult in our creative setting involving diverse clips. Code is available via the project page at https://kan32501.github.io/sage.github.io/.
Read the full abstract
Computer Vision
Group Relative Attention Guidance for Image Editing
Recently, image editing based on Diffusion-in-Transformer models has undergone rapid development. However, existing editing methods often lack effective control over the degree of editing, limiting their ability to achieve more customized results. To address this limitation, we investigate the MM-Attention mechanism within the DiT model and observe that the Query and Key tokens share a bias vector that is only layer-dependent. We interpret this bias as representing the model's inherent editing behavior, while the delta between each token and its corresponding bias encodes the content-specific editing signals. Based on this insight, we propose Group Relative Attention Guidance, a simple yet effective method that reweights the delta values of different tokens to modulate the focus of the model on the input image relative to the editing instruction, enabling continuous and fine-grained control over editing intensity without any tuning. Extensive experiments conducted on existing image editing frameworks demonstrate that GRAG can be integrated with as few as four lines of code, consistently enhancing editing quality. Moreover, compared to the commonly used Classifier-Free Guidance, GRAG achieves smoother and more precise control over the degree of editing. Our code will be released at https://github.com/little-misfit/GRAG-Image-Editing.