Peer Revenue Past citations are no guarantee of future returns

Papers

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

Computer Science Computer Vision

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

Tuesday 25 November

Computer Vision

WPT: World-to-Policy Transfer via Online World Model Distillation

Recent years have witnessed remarkable progress in world models, which primarily aim to capture the spatio-temporal correlations between an agent's actions and the evolving environment. However, existing approaches often suffer from tight runtime coupling or depend on offline reward signals, resulting in substantial inference overhead or hindering end-to-end optimization. To overcome these limitations, we introduce WPT, a World-to-Policy Transfer training paradigm that enables online distillation under the guidance of an end-to-end world model. Specifically, we develop a trainable reward model that infuses world knowledge into a teacher policy by aligning candidate trajectories with the future dynamics predicted by the world model. Subsequently, we propose policy distillation and world reward distillation to transfer the teacher's reasoning ability into a lightweight student policy, enhancing planning performance while preserving real-time deployability. Extensive experiments on both open-loop and closed-loop benchmarks show that our WPT achieves state-of-the-art performance with a simple policy architecture: it attains a 0.11 collision rate (open-loop) and achieves a 79.23 driving score (closed-loop) surpassing both world-model-based and imitation-learning methods in accuracy and safety. Moreover, the student sustains up to 4.9x faster inference, while retaining most of the gains.
Read the full abstract

All authors Guangfeng Jiang, Yueru Luo, Jun Liu, Yi Huang, Yiyao Zhu, Zhan Qu, Dave Zhenyu Chen, Bingbing Liu, Xu Yan

Computer Vision

Explainable Visual Anomaly Detection via Concept Bottleneck Models

In recent years, VAD (Visual Anomaly Detection) has attracted significant attention due to its high interpretability, as it provides visual explanations by highlighting anomalous regions within an image. However, although these visual explanations can be helpful, they lack a direct and semantically meaningful interpretation for users. To address this limitation, we propose extending CBMs (Concept Bottleneck Models) to the VAD setting. By learning meaningful concepts, the network can provide human-interpretable descriptions of anomalies, offering a novel and more insightful way to explain them. Our main contributions are: (i) we introduce a concept-based framework for anomaly explanation by extending CBMs to the VAD setting for the first time; (ii) we evaluate multiple supervision regimes, ranging from supervised to unsupervised anomaly settings; (iii) we propose a dual-branch architecture that combines a CBM-based Concept branch for concept-level explanations with a Visual branch for pixel-level anomaly localization, bridging semantic and spatial interpretability. When evaluated across three well-established VAD benchmarks, our approach, Concept-Aware Visual Anomaly Detection (\ourmethod), achieves performance comparable to classic VAD methods (up to 0.97 I-AUROC on MVTec AD) while providing richer, concept-driven explanations. A user study (582 responses) shows that \ourmethod{} explanations are rated effective in 73.5% of cases (vs. 60.7% for the SOTA VLM-based explainer Anomaly-OV) and misleading in only 3.1% (vs. 11.7%). Beyond explanation quality, CBMs enable human-in-the-loop correction: concept-level interventions further boost detection in the challenging unsupervised setting, closing part of the gap to fully supervised performance.
Read the full abstract

All authors Arianna Stropeni, Valentina Zaccaria, Francesco Borsatti, Davide Dalle Pezze, Manuel Barusco, Gian Antonio Susto

Computer Vision

Blind Adaptive Local Denoising for CEST Imaging

Chemical Exchange Saturation Transfer (CEST) MRI enables molecular-level visualization of low-concentration metabolites by leveraging proton exchange dynamics. However, its clinical translation is hindered by inherent challenges: spatially varying noise arising from hardware limitations, and complex imaging protocols introduce heteroscedasticity in CEST data, perturbing the accuracy of quantitative contrast mapping such as amide proton transfer (APT) imaging. Traditional denoising methods are not designed for this complex noise and often alter the underlying information that is critical for biomedical analysis. To overcome these limitations, we propose a new Blind Adaptive Local Denoising (BALD) method. BALD exploits the self-similar nature of CEST data to derive an adaptive variance-stabilizing transform that equalizes the noise distributions across CEST pixels without prior knowledge of noise characteristics. Then, BALD performs two-stage denoising on a linear transformation of data to disentangle molecular signals from noise. A local SVD decomposition is used as a linear transform to prevent spatial and spectral denoising artifacts. We conducted extensive validation experiments on multiple phantoms and in vivo CEST scans. In these experiments, BALD consistently outperformed state-of-the-art CEST denoisers in both denoising metrics and downstream tasks such as molecular concentration maps estimation and cancer detection.
Read the full abstract

All authors Chu Chen, Aitor Artola, Yang Liu, Se Weon Park, Raymond H. Chan, Jean-Michel Morel, Kannie W. Y. Chan

Computer Vision

Learning Procedural-aware Video Representations through State-Grounded Hierarchy Unfolding

Learning procedural-aware video representations is a key step towards building agents that can reason about and execute complex tasks. Existing methods typically address this problem by aligning visual content with textual descriptions at the task and step levels to inject procedural semantics into video representations. However, due to their high level of abstraction, 'task' and 'step' descriptions fail to form a robust alignment with the concrete, observable details in visual data. To address this, we introduce 'states', i.e., textual snapshots of object configurations, as a visually-grounded semantic layer that anchors abstract procedures to what a model can actually see. We formalize this insight in a novel Task-Step-State (TSS) framework, where tasks are achieved via steps that drive transitions between observable states. To enforce this structure, we propose a progressive pre-training strategy that unfolds the TSS hierarchy, forcing the model to ground representations in states while associating them with steps and high-level tasks. Extensive experiments on the COIN and CrossTask datasets show that our method outperforms baseline models on multiple downstream tasks, including task recognition, step recognition, and next step prediction. Ablation studies show that introducing state supervision is a key driver of performance gains across all tasks. Additionally, our progressive pretraining strategy proves more effective than standard joint training, as it better enforces the intended hierarchical structure.
Read the full abstract

Computer Vision

PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images

Autoregressive (AR) image generation has recently emerged as a powerful paradigm for image synthesis. Leveraging the generation principle of large language models, they allow for efficiently generating deceptively real-looking images, further increasing the need for reliable detection methods. However, to date there is a lack of work specifically targeting the detection of images generated by AR image generators. In this work, we present PRADA (Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images), a simple and interpretable approach that can reliably detect AR-generated images and attribute them to their respective source model. The key idea is to inspect the ratio of a model's conditional and unconditional probability for the autoregressive token sequence representing a given image. Whenever an image is generated by a particular model, its probability ratio shows unique characteristics which are not present for images generated by other models or real images. We exploit these characteristics for threshold-based attribution and detection by calibrating a simple, model-specific score function. Our experimental evaluation shows that PRADA is highly effective against eight class-to-image and four text-to-image models. We release our code and data at github.com/jonasricker/prada.
Read the full abstract

All authors Simon Damm, Jonas Ricker, Henning Petzka, Asja Fischer

Computer Vision

FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds

Point cloud compression methods jointly optimize bitrates and reconstruction distortion. However, balancing compression ratio and reconstruction quality is difficult because low-frequency and high-frequency components contribute differently at the same resolution. To address this, we propose FLaTEC, a frequency-aware compression model that enables the compression of a full scan with high compression ratios. Our approach introduces a frequency-aware mechanism that decouples low-frequency structures and high-frequency textures, while hybridizing latent triplanes as a compact proxy for point cloud. Specifically, we convert voxelized embeddings into triplane representations to reduce sparsity, computational cost, and storage requirements. We then devise a frequency-disentangling technique that extracts compact low-frequency content while collecting high-frequency details across scales. The decoupled low-frequency and high-frequency components are stored in binary format. During decoding, full-spectrum signals are progressively recovered via a modulation block. Additionally, to compensate for the loss of 3D correlation, we introduce an efficient frequency-based attention mechanism that fosters local connectivity and outputs arbitrary resolution points. Our method achieves state-of-the-art rate-distortion performance and outperforms the standard codecs by 78% and 94% in BD-rate on both SemanticKITTI and Ford datasets.
Read the full abstract

All authors Xiaoge Zhang, Zijie Wu, Mingtao Feng, Zichen Geng, Mehwish Nasim, Saeed Anwar, Ajmal Mian

Computer Vision

DeLightMono: Enhancing Self-Supervised Monocular Depth Estimation in Endoscopy by Decoupling Uneven Illumination

Self-supervised monocular depth estimation serves as a key task in the development of endoscopic navigation systems. However, performance degradation persists due to uneven illumination inherent in endoscopic images, particularly in low-intensity regions. Existing low-light enhancement techniques fail to effectively guide the depth network. Furthermore, solutions from other fields, like autonomous driving, require well-lit images, making them unsuitable and increasing data collection burdens. To this end, we present DeLight-Mono - a novel self-supervised monocular depth estimation framework with illumination decoupling. Specifically, endoscopic images are represented by a designed illumination-reflectance-depth model, and are decomposed with auxiliary networks. Moreover, a self-supervised joint-optimizing framework with novel losses leveraging the decoupled components is proposed to mitigate the effects of uneven illumination on depth estimation. The effectiveness of the proposed methods was rigorously verified through extensive comparisons and an ablation study performed on two public datasets.
Read the full abstract

All authors Mingyang Ou, Haojin Li, Yifeng Zhang, Ke Niu, Zhongxi Qiu, Heng Li, Jiang Liu

Computer Vision

History-Augmented Contrastive Learning With Soft Mixture of Experts for Blind Super-Resolution of Planetary Remote Sensing Images

Blind Super-Resolution (BSR) in planetary remote sensing constitutes a highly ill-posed inverse problem, characterized by unknown degradation patterns and a complete absence of ground-truth supervision. Existing unsupervised approaches often struggle with optimization instability and distribution shifts, relying on greedy strategies or generic priors that fail to preserve distinct morphological semantics. To address these challenges, we propose History-Augmented Contrastive Mixture of Experts (HAC-MoE), a novel unsupervised framework that decouples kernel estimation from image reconstruction without external kernel priors. The framework is founded on three key innovations: (1) A Contrastive Kernel Sampling mechanism that mitigates the distribution bias inherent in random Gaussian sampling, ensuring the generation of plausible kernel priors via similarity constraints; (2) A History-Augmented Contrastive Learning strategy that leverages historical model states as negative self-priors. We provide a theoretical analysis demonstrating that this mechanism induces strong convexity in the feature space, thereby stabilizing the unsupervised optimization trajectory and preventing overfitting; and (3) A Morphology-Aware Soft Mixture-of-Experts (MA-MoE) estimator that dynamically modulates spectral-spatial features to adaptively reconstruct diverse planetary topographies. To facilitate rigorous evaluation, we introduce Ceres-50, a benchmark dataset encapsulating diverse geological features under realistic degradation simulations. Extensive experiments demonstrate that HAC-MoE achieves state-of-the-art performance in reconstruction quality and kernel estimation accuracy, offering a solution for scientific observation in data-sparse extraterrestrial environments.
Read the full abstract

All authors Hui-Jia Zhao, Jie Lu, Yunqing Jiang, Xiao-Ping Lu, Kaichang Di

Computer Vision

MFM-point: Multi-scale Flow Matching for Point Cloud Generation

In recent years, point cloud generation has gained significant attention in 3D generative modeling. Among existing approaches, point-based methods directly generate point clouds without relying on other representations such as latent features, meshes, or voxels. These methods offer low training cost and algorithmic simplicity, but often underperform compared to representation-based approaches. In this paper, we propose MFM-Point, a multi-scale Flow Matching framework for point cloud generation that substantially improves the scalability and performance of point-based methods while preserving their simplicity and efficiency. Our multi-scale generation algorithm adopts a coarse-to-fine generation paradigm, enhancing generation quality and scalability without incurring additional training or inference overhead. A key challenge in developing such a multi-scale framework lies in preserving the geometric structure of unordered point clouds while ensuring smooth and consistent distributional transitions across resolutions. To address this, we introduce a structured downsampling and upsampling strategy that preserves geometry and maintains alignment between coarse and fine resolutions. Our experimental results demonstrate that MFM-Point achieves best-in-class performance among point-based methods and challenges the best representation-based methods. In particular, MFM-point demonstrates strong results in multi-category and high-resolution generation tasks.
Read the full abstract

All authors Petr Molodyk, Jaemoo Choi, David W. Romero, Ming-Yu Liu, Yongxin Chen

Computer Vision

Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization

Image vectorization aims to convert raster images into editable, scalable vector representations while preserving visual fidelity. Existing vectorization methods struggle to represent complex real-world images, often producing fragmented shapes at the cost of semantic conciseness. In this paper, we propose COVec, an illumination-aware vectorization framework inspired by the Clair-Obscur principle of light-shade contrast. COVec is the first to introduce intrinsic image decomposition in the vector domain, separating an image into albedo, shade, and light layers in a unified vector representation. A semantic-guided initialization and two-stage optimization refine these layers with differentiable rendering. Experiments on various datasets demonstrate that COVec achieves higher visual fidelity and significantly improved editability compared to existing methods. The code will be released at https://github.com/decade-de/COVec.
Read the full abstract

All authors Xingyue Lin, Shuai Peng, Xiangyu Xie, Jianhua Zhu, Yuxuan Zhou, Liangcai Gao

Computer Vision

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention

Visual attention serves as the primary mechanism through which MLLMs interpret visual information; however, its limited localization capability often leads to hallucinations. We observe that although MLLMs can accurately extract visual semantics from visual tokens, they fail to fully leverage this advantage during subsequent inference. To address this limitation, we propose Vision-Guided Attention (VGA), a training-free method that first constructs precise visual grounding by exploiting the semantic content of visual tokens, and then uses this grounding to guide the model's focus toward relevant visual regions. In image captioning, VGA further refines this guidance dynamically during generation by suppressing regions that have already been described. In VGA, each token undergoes only a single forward pass, introducing a negligible latency overhead. In addition, VGA is fully compatible with efficient attention implementations such as FlashAttention. Extensive experiments across diverse MLLMs and multiple hallucination benchmarks demonstrate that VGA achieves state-of-the-art dehallucination performance. Further analysis confirms that explicit visual guidance plays a crucial role in enhancing the visual understanding capabilities of MLLMs.
Read the full abstract

All authors Jianfei Zhao, Feng Zhang, Xin Sun, Chong Feng, Zhixing Tan

Computer Vision

SAM-MI: A Mask-Injected Framework for Enhancing Open-Vocabulary Semantic Segmentation with SAM

Open-vocabulary semantic segmentation (OVSS) aims to segment and recognize objects universally. Trained on extensive high-quality segmentation data, the segment anything model (SAM) has demonstrated remarkable universal segmentation capabilities, offering valuable support for OVSS. Although previous methods have made progress in leveraging SAM for OVSS, there are still some challenges: (1) SAM's tendency to over-segment and (2) hard combinations between fixed masks and labels. This paper introduces a novel mask-injected framework, SAM-MI, which effectively integrates SAM with OVSS models to address these challenges. Initially, SAM-MI employs a Text-guided Sparse Point Prompter to sample sparse prompts for SAM instead of previous dense grid-like prompts, thus significantly accelerating the mask generation process. The framework then introduces Shallow Mask Aggregation (SMAgg) to merge partial masks to mitigate the SAM's over-segmentation issue. Finally, Decoupled Mask Injection (DMI) incorporates SAM-generated masks for guidance at low-frequency and high-frequency separately, rather than directly combining them with labels. Extensive experiments on multiple benchmarks validate the superiority of SAM-MI. Notably, the proposed method achieves a 16.7% relative improvement in mIoU over Grounded-SAM on the MESS benchmark, along with a 1.6$\times$ speedup. We hope SAM-MI can serve as an alternative methodology to effectively equip the OVSS model with SAM.
Read the full abstract

All authors Lin Chen, Yingjian Zhu, Qi Yang, Xin Niu, Kun Ding, Shiming Xiang

Computer Vision

WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving

Recent advancements in multimodal large language models (MLLMs) have shown strong understanding of driving scenes, drawing interest in their application to autonomous driving. However, high-level reasoning in safety-critical scenarios, where avoiding one traffic risk can create another, remains a major challenge. Such reasoning is often infeasible with only a single front view and requires a comprehensive view of the environment, which we achieve through multi-view inputs. We define Safety-Critical Reasoning as a new task that leverages multi-view inputs to address this challenge. Then, we distill Safety-Critical Reasoning into two stages: first resolve the immediate risk, then mitigate the decision-induced downstream risks. To support this, we introduce WaymoQA, a dataset of 35,000 human-annotated question-answer pairs covering complex, high-risk driving scenarios. The dataset includes multiple-choice and open-ended formats across both image and video modalities. Experiments reveal that existing MLLMs underperform in safety-critical scenarios compared to normal scenes, but fine-tuning with WaymoQA significantly improves their reasoning ability, highlighting the effectiveness of our dataset in developing safer and more reasoning-capable driving agents. Our code and data are provided in https://github.com/sjyu001/WaymoQA
Read the full abstract

All authors Seungjun Yu, Seonho Lee, Namho Kim, Jaeyo Shin, Junsung Park, Wonjeong Ryu, Raehyuk Jung, Hyunjung Shim

Computer Vision

ACIT: Attention-Guided Cross-Modal Interaction Transformer for Pedestrian Crossing Intention Prediction

Predicting pedestrian crossing intention is crucial for autonomous vehicles to prevent pedestrian-related collisions. However, effectively extracting and integrating complementary cues from different types of data remains one of the major challenges. This paper proposes an attention-guided cross-modal interaction Transformer (ACIT) for pedestrian crossing intention prediction. ACIT leverages six visual and motion modalities, which are grouped into three interaction pairs: (1) Global semantic map and global optical flow, (2) Local RGB image and local optical flow, and (3) Ego-vehicle speed and pedestrian's bounding box. Within each visual interaction pair, a dual-path attention mechanism enhances salient regions within the primary modality through intra-modal self-attention and facilitates deep interactions with the auxiliary modality (i.e., optical flow) via optical flow-guided attention. Within the motion interaction pair, cross-modal attention is employed to model the cross-modal dynamics, enabling the effective extraction of complementary motion features. Beyond pairwise interactions, a multi-modal feature fusion module further facilitates cross-modal interactions at each time step. Furthermore, a Transformer-based temporal feature aggregation module is introduced to capture sequential dependencies. Experimental results demonstrate that ACIT outperforms state-of-the-art methods, achieving accuracy rates of 70% and 89% on the JAADbeh and JAADall datasets, respectively. Extensive ablation studies are further conducted to investigate the contribution of different modules of ACIT.
Read the full abstract

Computer Vision

Multi-Context Fusion Transformer for Pedestrian Crossing Intention Prediction in Urban Environments

Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. However, accurate pedestrian intention prediction in urban environments remains challenging due to the multitude of factors affecting pedestrian behavior. In this paper, we propose a multi-context fusion Transformer (MFT) that leverages diverse numerical contextual attributes across four key dimensions, encompassing pedestrian behavior context, environmental context, pedestrian localization context and vehicle motion context, to enable accurate pedestrian intention prediction. MFT employs a progressive fusion strategy, where mutual intra-context attention enables reciprocal interactions within each context, thereby facilitating feature sequence fusion and yielding a context token as a context-specific representation. This is followed by mutual cross-context attention, which integrates features across contexts with a global CLS token serving as a compact multi-context representation. Finally, guided intra-context attention refines context tokens within each context through directed interactions, while guided cross-context attention strengthens the global CLS token to promote multi-context fusion via guided information propagation, yielding deeper and more efficient integration. Experimental results validate the superiority of MFT over state-of-the-art methods, achieving accuracy rates of 73%, 93%, and 90% on the JAADbeh, JAADall, and PIE datasets, respectively. Extensive ablation studies are further conducted to investigate the effectiveness of the network architecture and contribution of different input context. Our code is open-source: https://github.com/ZhongHang0307/Multi-Context-Fusion-Transformer.
Read the full abstract

Computer Vision

Pedestrian Crossing Intention Prediction Using Multimodal Fusion Network

Pedestrian crossing intention prediction is essential for the deployment of autonomous vehicles (AVs) in urban environments. Ideal prediction provides AVs with critical environmental cues, thereby reducing the risk of pedestrian-related collisions. However, the prediction task is challenging due to the diverse nature of pedestrian behavior and its dependence on multiple contextual factors. This paper proposes a multimodal fusion network that leverages seven modality features from both visual and motion branches, aiming to effectively extract and integrate complementary cues across different modalities. Specifically, motion and visual features are extracted from the raw inputs using multiple Transformer-based extraction modules. Depth-guided attention module leverages depth information to guide attention towards salient regions in another modality through comprehensive spatial feature interactions. To account for the varying importance of different modalities and frames, modality attention and temporal attention are designed to selectively emphasize informative modalities and effectively capture temporal dependencies. Extensive experiments on the JAAD dataset validate the effectiveness of the proposed network, achieving superior performance compared to the baseline methods.
Read the full abstract

Computer Vision · Cross-listed from cs.LG

Zero-Shot Transfer Capabilities of the Sundial Foundation Model for Leaf Area Index Forecasting

This work investigates the zero-shot forecasting capability of time series foundation models for Leaf Area Index (LAI) forecasting in agricultural monitoring. Using the HiQ dataset (U.S., 2000-2022), we systematically compare statistical baselines, a fully supervised LSTM, and the Sundial foundation model under multiple evaluation protocols. We find that Sundial, in the zero-shot setting, can outperform a fully trained LSTM provided that the input context window is sufficiently long-specifically, when covering more than one or two full seasonal cycles. We show that a general-purpose foundation model can surpass specialized supervised models on remote-sensing time series prediction without any task-specific tuning. These results highlight the strong potential of pretrained time series foundation models to serve as effective plug-and-play forecasters in agricultural and environmental applications.
Read the full abstract

All authors Peining Zhang, Hongchen Qin, Haochen Zhang, Ziqi Guo, Guiling Wang, Jinbo Bi

Computer Vision · Cross-listed from eess.SP

Redefining Radar Segmentation: Simultaneous Static-Moving Segmentation and Ego-Motion Estimation using Radar Point Clouds

Conventional radar segmentation research has typically focused on learning category labels for different moving objects. Although fundamental differences between radar and optical sensors lead to differences in the reliability of predicting accurate and consistent category labels, a review of common radar perception tasks in automotive reveals that determining whether an object is moving or static is a prerequisite for most tasks. To fill this gap, this study proposes a neural network based solution that can simultaneously segment static and moving objects from radar point clouds. Furthermore, since the measured radial velocity of static objects is correlated with the motion of the radar, this approach can also estimate the instantaneous 2D velocity of the moving platform or vehicle (ego motion). However, despite performing dual tasks, the proposed method employs very simple yet effective building blocks for feature extraction: multi layer perceptrons (MLPs) and recurrent neural networks (RNNs). In addition to being the first of its kind in the literature, the proposed method also demonstrates the feasibility of extracting the information required for the dual task directly from unprocessed point clouds, without the need for cloud aggregation, Doppler compensation, motion compensation, or any other intermediate signal processing steps. To measure its performance, this study introduces a set of novel evaluation metrics and tests the proposed method using a challenging real world radar dataset, RadarScenes. The results show that the proposed method not only performs well on the dual tasks, but also has broad application potential in other radar perception tasks.
Read the full abstract

All authors Simin Zhu, Satish Ravindran, Alexander Yarovoy, Francesco Fioranelli

Computer Vision

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibility of hijacking multiple stateless decisions simultaneously using a single universal perturbation. We introduce the Semantic-Aware Universal Perturbation (SAUP), which acts as a semantic router, "actively" perceiving input semantics and routing them to distinct, attacker-defined targets. To achieve this, we conduct theoretical and empirical analysis on the geometric properties in the latent space. Guided by these insights, we propose the Semantic-Oriented (SORT) optimization strategy and annotate a new dataset with fine-grained semantics to evaluate performance. Extensive experiments on three representative MLLMs demonstrate the fundamental feasibility of this attack, achieving a 66% attack success rate over five targets using a single frame against Qwen.
Read the full abstract

All authors Changyue Li, Jiaying Li, Youliang Yuan, Jiaming He, Zhicong Huang, Pinjia He

Computer Vision

CREward: A Type-Specific Creativity Reward Model

Creativity is a complex phenomenon. When it comes to representing and assessing creativity, treating it as a single undifferentiated quantity would appear naive and underwhelming. In this work, we learn the first type-specific creativity reward model, coined CREward, which spans three creativity “axes," geometry, material, and texture, to allow us to view creativity through the lens of the image formation pipeline. To build our reward model, we first conduct a human benchmark evaluation to capture human perception of creativity for each type across various creative images. We then analyze the correlation between human judgments and predictions by large vision-language models (LVLMs), confirming that LVLMs exhibit strong alignment with human perception. Building on this observation, we collect LVLM-generated labels to train our CREward model that is applicable to both evaluation and generation of creative images. We explore three applications of CREward: creativity assessment, explainable creativity, and creative sample acquisition for both human design inspiration and guiding creative generation through low-rank adaptation.
Read the full abstract

All authors Jiyeon Han, Ali Mahdavi-Amiri, Hao Zhang, Haedong Jeong

Computer Vision

OmniRefiner: Reinforcement-Guided Local Diffusion Refinement

Reference-guided image generation has progressed rapidly, yet current diffusion models still struggle to preserve fine-grained visual details when refining a generated image using a reference. This limitation arises because VAE-based latent compression inherently discards subtle texture information, causing identity- and attribute-specific cues to vanish. Moreover, post-editing approaches that amplify local details based on existing methods often produce results inconsistent with the original image in terms of lighting, texture, or shape. To address this, we introduce \ourMthd{}, a detail-aware refinement framework that performs two consecutive stages of reference-driven correction to enhance pixel-level consistency. We first adapt a single-image diffusion editor by fine-tuning it to jointly ingest the draft image and the reference image, enabling globally coherent refinement while maintaining structural fidelity. We then apply reinforcement learning to further strengthen localized editing capability, explicitly optimizing for detail accuracy and semantic consistency. Extensive experiments demonstrate that \ourMthd{} significantly improves reference alignment and fine-grained detail preservation, producing faithful and visually coherent edits that surpass both open-source and commercial models on challenging reference-guided restoration benchmarks.
Read the full abstract

All authors Yaoli Liu, Ziheng Ouyang, Shengtao Lou, Yiren Song

Computer Vision

GazeProphetV2: Head-Movement-Based Gaze Prediction Enabling Efficient Foveated Rendering on Mobile VR

Predicting gaze behavior in virtual reality environments remains a significant challenge with implications for rendering optimization and interface design. This paper introduces a multimodal approach to VR gaze prediction that combines temporal gaze patterns, head movement data, and visual scene information. By leveraging a gated fusion mechanism with cross-modal attention, the approach learns to adaptively weight gaze history, head movement, and scene content based on contextual relevance. Evaluations using a dataset spanning 22 VR scenes with 5.3M gaze samples demonstrate improvements in predictive accuracy when combining modalities compared to using individual data streams alone. The results indicate that integrating past gaze trajectories with head orientation and scene content enhances prediction accuracy across 1-3 future frames. Cross-scene generalization testing shows consistent performance with 93.1% validation accuracy and temporal consistency in predicted gaze trajectories. These findings contribute to understanding attention mechanisms in virtual environments while suggesting potential applications in rendering optimization, interaction design, and user experience evaluation. The approach represents a step toward more efficient virtual reality systems that can anticipate user attention patterns without requiring expensive eye tracking hardware.
Read the full abstract

All authors Farhaan Ebadulla, Chiraag Mudlpaur, Shreya Chaurasia, Gaurav BV

Computer Vision · Cross-listed from cs.LG

On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices

Sparsity is essential for deploying large models on resource constrained edge platforms. However, optimizing sparsity patterns for individual tasks in isolation ignores the significant I/O overhead incurred during frequent task switching. We introduce an on-demand multi-task sparsity framework specifically designed to minimize switching costs by maximizing parameter reuse. Unlike monolithic approaches, we decompose weights into reusable block-granular units and align sparse structures across tasks to maximize overlap. By dynamically loading only the small differential set of blocks required for the next task, our method effectively mitigates the cold-start latency inherent in traditional monolithic approaches.Experiments on a real-world autonomous driving platform demonstrate that our framework achieves superior switching efficiency, accelerating task switching by over 6.6X on average compared to existing sparsity methods.
Read the full abstract

All authors Lianming Huang, Haibo Hu, Qiao Li, Nan Guan, Chun Jason Xue

Computer Vision

SONIC: Spectral Optimization of Noise for Inpainting with Consistency

We propose a novel training-free method for inpainting with off-the-shelf text-to-image models. While guidance-based methods in theory allow generic models to be used for inverse problems such as inpainting – in practice their effectiveness is limited, leading to the necessity of specialized inpainting-specific models. In this work, we argue the missing ingredient for training-free generic model usage is proper optimization of the initial noise sample. We optimize the initial noise to approximately reproduce the unmasked image, in as few as tens of optimization steps, then use it with a conventional training-free inpainting method. Critically, we propose two core ideas that make this possible: (i) we perform linear approximation that avoids the costly and often impractical unrolling required to relate the initial noise sample to model output – which potentially is why this relationship was previously overlooked; and (ii) perform spectral preconditioning by optimizing the initial noise sample in the spectral domain with Adam, which stabilizes the optimization. We demonstrate our method on various inpainting tasks, outperforming the state of the art. Project website: https://ubc-vision.github.io/sonic/
Read the full abstract

All authors Seungyeon Baek, Erqun Dong, Shadan Namazifard, Mark J. Matthews, Kwang Moo Yi

Computer Vision

EmoFeedback$^2$: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedback

Continuous emotional image content generation (C-EICG) is emerging rapidly due to its ability to produce images aligned with both user descriptions and continuous emotional values. However, existing approaches lack emotional feedback from generated images, limiting the control of emotional continuity. Additionally, their simple emotion-text alignment fails to adaptively adjust emotional prompts according to image content, leading to insufficient emotional fidelity. To address these concerns, we propose a novel generation-understanding-feedback reinforcement paradigm (EmoFeedback$^2$) for C-EICG, which exploits the reasoning capability of the fine-tuned large vision-language model (LVLM) to provide reward and textual feedback for generating high-quality images with continuous emotions. Specifically, we introduce an emotion-aware reward feedback strategy, where the LVLM evaluates the emotional values of generated images and computes the reward against target emotions, guiding the reinforcement fine-tuning of the generative model and enhancing the emotional continuity of images. Furthermore, we design a self-promotion textual feedback framework, in which the LVLM iteratively analyzes the emotional content of generated images and adaptively produces refinement suggestions for the next-round prompt, improving the emotional fidelity with fine-grained content. Extensive experimental results demonstrate that our approach effectively generates high-quality images with the desired emotions, outperforming existing state-of-the-art methods on both our custom dataset and public dataset.
Read the full abstract

All authors Kai Shu, Jingyang Jia, Gang Yang, Long Xing, Xun Chen, Aiping Liu

Computer Vision

Boosting Reasoning in Large Multimodal Models via Activation Replay

Recently, Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach to incentivizing reasoning capability in Large Multimodal Models (LMMs), while the underlying mechanisms behind this post-training paradigm are poorly understood. We begin by exploring how input activations are affected by RLVR through the perspective of logit lens. Our systematic investigations across multiple post-trained LMMs suggest that RLVR shifts low-entropy activations unexpectedly, while high-entropy ones are less affected. We further demonstrate that such phenomena are associated with LMM reasoning by controlled experiments, suggesting a potentially beneficial role of modulating low-entropy activations. To this end, we propose Activation Replay, a novel simple yet effective training-free approach that boosts multimodal reasoning of post-trained LMMs without requiring expensive policy optimization. Our design involves manipulation of visual tokens at test time, replaying low-entropy activations from the input context of base LMMs to regulating the RLVR counterparts. Activation Replay triggers better reasoning across diverse scenarios, including mathematics, o3-like visual agents, and video reasoning. We further show that Activation Replay boosts Pass@K and mitigates narrower reasoning coverage of RLVR. Our design is compared against alternative choices, such as replaying high-entropy activations instead of low-entropy ones, or direct cross-model intervention instead of manipulating input tokens, demonstrating the superiority of our implementation. Code is publicly available at https://github.com/latentcraft/replay.
Read the full abstract

All authors Yun Xing, Xiaobin Hu, Qingdong He, Jiangning Zhang, Shuicheng Yan, Shijian Lu, Yu-Gang Jiang

Computer Vision

VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction

Reconstructing dynamic 4D scenes is challenging, as it requires robust disentanglement of dynamic objects from the static background. While 3D foundation models like VGGT provide accurate 3D geometry, their performance drops markedly when moving objects dominate. Existing 4D approaches often rely on external priors, heavy post-optimization, or require fine-tuning on 4D datasets. In this paper, we propose VGGT4D, a training-free framework that extends the 3D foundation model VGGT for robust 4D scene reconstruction. Our approach is motivated by the key finding that VGGT's global attention layers already implicitly encode rich, layer-wise dynamic cues. To obtain masks that decouple static and dynamic elements, we mine and amplify global dynamic cues via gram similarity and aggregate them across a temporal window. To further sharpen mask boundaries, we introduce a refinement strategy driven by projection gradient. We then integrate these precise masks into VGGT's early-stage inference, effectively mitigating motion interference in both pose estimation and geometric reconstruction. Across six datasets, our method achieves superior performance in dynamic object segmentation, camera pose estimation, and dense reconstruction. It also supports single-pass inference on sequences longer than 500 frames.
Read the full abstract

All authors Yu Hu, Chong Cheng, Sicheng Yu, Xiaoyang Guo, Hao Wang

Computer Vision

HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning

Recent advances in diffusion models have demonstrated impressive capability in generating high-quality images for simple prompts. However, when confronted with complex prompts involving multiple objects and hierarchical structures, existing models struggle to accurately follow instructions, leading to issues such as concept omission, confusion, and poor compositionality. To address these limitations, we propose a Hierarchical Compositional Generative framework (HiCoGen) built upon a novel Chain of Synthesis (CoS) paradigm. Instead of monolithic generation, HiCoGen first leverages a Large Language Model (LLM) to decompose complex prompts into minimal semantic units. It then synthesizes these units iteratively, where the image generated in each step provides crucial visual context for the next, ensuring all textual concepts are faithfully constructed into the final scene. To further optimize this process, we introduce a reinforcement learning (RL) framework. Crucially, we identify that the limited exploration of standard diffusion samplers hinders effective RL. We theoretically prove that sample diversity is maximized by concentrating stochasticity in the early generation stages and, based on this insight, propose a novel Decaying Stochasticity Schedule to enhance exploration. Our RL algorithm is then guided by a hierarchical reward mechanism that jointly evaluates the image at the global, subject, and relationship levels. We also construct HiCoPrompt, a new text-to-image benchmark with hierarchical prompts for rigorous evaluation. Experiments show our approach significantly outperforms existing methods in both concept coverage and compositional accuracy.
Read the full abstract

All authors Hongji Yang, Yucheng Zhou, Wencheng Han, Runzhou Tao, Zhongying Qiu, Jianfei Yang, Jianbing Shen

Computer Vision

MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing

Despite decades of progress, a truly input-size agnostic visual encoder-a fundamental characteristic of human vision-has remained elusive. We address this limitation by proposing MambaEye, a novel, causal sequential encoder that leverages the low complexity and causal-process based pure Mamba2 backbone. Unlike previous Mamba-based vision encoders that often employ bidirectional processing, our strictly unidirectional approach preserves the inherent causality of State Space Models, enabling the model to generate a prediction at any point in its input sequence. A core innovation is our use of relative move embedding, which encodes the spatial shift between consecutive patches, providing a strong inductive bias for translation invariance and making the model inherently adaptable to arbitrary image resolutions and scanning patterns. To achieve this, we introduce a novel diffusion-inspired loss function that provides dense, step-wise supervision, training the model to build confidence as it gathers more visual evidence. We demonstrate that MambaEye exhibits robust performance across a wide range of image resolutions, especially at higher resolutions such as $1536^2$ on the ImageNet-1K classification task. This feat is achieved while maintaining linear time and memory complexity relative to the number of patches.
Read the full abstract

Computer Vision

GFT-GCN: Privacy-Preserving 3D Face Mesh Recognition with Spectral Diffusion

3D face recognition offers a robust biometric solution by capturing facial geometry, providing resilience to variations in illumination, pose changes, and presentation attacks. Its strong spoof resistance makes it suitable for high-security applications, but protecting stored biometric templates remains critical. We present GFT-GCN, a privacy-preserving 3D face recognition framework that combines spectral graph learning with diffusion-based template protection. Our approach integrates the Graph Fourier Transform (GFT) and Graph Convolutional Networks (GCN) to extract compact, discriminative spectral features from 3D face meshes. To secure these features, we introduce a spectral diffusion mechanism that produces irreversible, renewable, and unlinkable templates. A lightweight client-server architecture ensures that raw biometric data never leaves the client device. Experiments on the BU-3DFE and FaceScape datasets demonstrate high recognition accuracy and strong resistance to reconstruction attacks. Results show that GFT-GCN effectively balances privacy and performance, offering a practical solution for secure 3D face authentication.
Read the full abstract