Computer Vision · Cross-listed from eess.IV
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Thursday 9 October
Traumatic brain injuries present significant diagnostic challenges in emergency medicine, where the timely interpretation of medical images is crucial for patient outcomes. In this paper, we propose a novel AI-based approach for automatic radiology report generation tailored to cranial trauma cases. Our model integrates an AC-BiFPN with a Transformer architecture to capture and process complex medical imaging data such as CT and MRI scans. The AC-BiFPN extracts multi-scale features, enabling the detection of intricate anomalies like intracranial hemorrhages, while the Transformer generates coherent, contextually relevant diagnostic reports by modeling long-range dependencies. We evaluate the performance of our model on the RSNA Intracranial Hemorrhage Detection dataset, where it outperforms traditional CNN-based models in both diagnostic accuracy and report generation. This solution not only supports radiologists in high-pressure environments but also provides a powerful educational tool for trainee physicians, offering real-time feedback and enhancing their learning experience. Our findings demonstrate the potential of combining advanced feature extraction with transformer-based text generation to improve clinical decision-making in the diagnosis of traumatic brain injuries.
Computer Vision · Cross-listed from cs.LG
Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
Traditional multimodal learners find unified representations for tasks like visual question answering, but rely heavily on paired datasets. However, an overlooked yet potentially powerful question is: can one leverage auxiliary unpaired multimodal data to directly enhance representation learning in a target modality? We introduce UML: Unpaired Multimodal Learner, a modality-agnostic training paradigm in which a single model alternately processes inputs from different modalities while sharing parameters across them. This design exploits the assumption that different modalities are projections of a shared underlying reality, allowing the model to benefit from cross-modal structure without requiring explicit pairs. Theoretically, under linear data-generating assumptions, we show that unpaired auxiliary data can yield representations strictly more informative about the data-generating process than unimodal training. Empirically, we show that using unpaired data from auxiliary modalities – such as text, audio, or images – consistently improves downstream performance across diverse unimodal targets such as image and audio. Our project page: https://unpaired-multimodal.github.io/
Read the full abstract
Computer Vision · Cross-listed from cs.GR
Splat the Net: Radiance Fields with Splattable Neural Primitives
Radiance fields have emerged as a predominant representation for modeling 3D scene appearance. Neural formulations such as Neural Radiance Fields provide high expressivity but require costly ray marching for rendering, whereas primitive-based methods such as 3D Gaussian Splatting offer real-time efficiency through splatting, yet at the expense of representational power. Inspired by advances in both these directions, we introduce splattable neural primitives, a new volumetric representation that reconciles the expressivity of neural models with the efficiency of primitive-based splatting. Each primitive encodes a bounded neural density field parameterized by a shallow neural network. Our formulation admits an exact analytical solution for line integrals, enabling efficient computation of perspectively accurate splatting kernels. As a result, our representation supports integration along view rays without the need for costly ray marching. The primitives flexibly adapt to scene geometry and, being larger than prior analytic primitives, reduce the number required per scene. On novel-view synthesis benchmarks, our approach matches the quality and speed of 3D Gaussian Splatting while using $10\times$ fewer primitives and $6\times$ fewer parameters. These advantages arise directly from the representation itself, without reliance on complex control or adaptation frameworks. The project page is https://vcai.mpi-inf.mpg.de/projects/SplatNet/.
Read the full abstract
Computer Vision
InstructX: Towards Unified Visual Editing with MLLM Guidance
With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most studies lack an in-depth analysis of MLLM design choices. Moreover, the integration of MLLMs and diffusion models remains an open challenge in some difficult tasks, such as video editing. In this paper, we present InstructX, a unified framework for image and video editing. Specifically, we conduct a comprehensive study on integrating MLLMs and diffusion models for instruction-driven editing across diverse tasks. Building on this study, we analyze the cooperation and distinction between images and videos in unified modeling. (1) We show that training on image data can lead to emergent video editing capabilities without explicit supervision, thereby alleviating the constraints imposed by scarce video training data. (2) By incorporating modality-specific MLLM features, our approach effectively unifies image and video editing tasks within a single model. Extensive experiments demonstrate that our method can handle a broad range of image and video editing tasks and achieves state-of-the-art performance.
Read the full abstract
Computer Vision
The Visual Iconicity Challenge: Evaluating Vision-Language Models on Sign Language Form-Meaning Mapping
Iconicity, the resemblance between linguistic form and meaning, is pervasive in signed languages, offering a natural testbed for visual grounding. For vision-language models (VLMs), the challenge is to recover such essential mappings from dynamic human motion rather than static context. We introduce the Visual Iconicity Challenge, a novel video-based benchmark that adapts psycholinguistic measures to evaluate VLMs on three tasks: (i) phonological sign-form prediction (e.g., handshape, location), (ii) transparency (inferring meaning from visual form), and (iii) graded iconicity ratings. We assess 13 state-of-the-art VLMs in zero- and few-shot settings on Sign Language of the Netherlands and compare them to human baselines. On phonological form prediction, VLMs recover some handshape and location detail but remain below human performance; on transparency, they are far from human baselines; and only top models correlate moderately with human iconicity ratings. Interestingly, models with stronger phonological form prediction correlate better with human iconicity judgment, indicating shared sensitivity to visually grounded structure. Our findings validate these diagnostic tasks and motivate human-centric signals and embodied learning methods for modelling iconicity and improving visual grounding in multimodal models.
Read the full abstract
Computer Vision
Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools
Multimodal large language models (MLLMs) have demonstrated remarkable potential in bridging visual and textual reasoning, yet their reliance on text-centric priors often limits their ability to disentangle semantically similar actions in open-vocabulary scenarios. To address this, we propose Video-STAR, a framework that harmonizes contextual sub-motion decomposition with tool-augmented reinforcement learning for open-vocabulary action recognition (OVAR). Unlike prior methods that treat actions as monolithic entities, our approach innovatively decomposes actions into discriminative sub-motions for fine-grained matching while dynamically invoking domain-specific tools for cross-modal interleaving, thereby enabling category-specific reasoning capacity and reducing cross-modal hallucination. Moreover, by designing a hierarchical reward that balances tool-usage efficiency, sub-motion relevance, and structural coherence in reasoning, our method autonomously leverages external tools to prioritize sub-motion patterns without explicit supervision, transmitting from text-centric reasoning to visually grounded inference. Extensive evaluations on HMDB-51, UCF-101, SSv2, Kinetics-400, and Kinetics-600 datasets demonstrate our state-of-the-art performance, outperforming existing methods in distinguishing fine-grained actions and handling cross-modal hallucination, validating our excellent robustness and generalization.
Read the full abstract
Computer Vision · Cross-listed from cs.RO
DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos
We present DexMan, an automated framework that converts human visual demonstrations into bimanual dexterous manipulation skills for humanoid robots in simulation. Operating directly on third-person videos of humans manipulating rigid objects, DexMan eliminates the need for camera calibration, depth sensors, scanned 3D object assets, or ground-truth hand and object motion annotations. Unlike prior approaches that consider only simplified floating hands, it directly controls a humanoid robot and leverages novel contact-based rewards to improve policy learning from noisy hand-object poses estimated from in-the-wild videos. DexMan achieves state-of-the-art performance in object pose estimation on the TACO benchmark, with absolute gains of 0.08 and 0.12 in ADD-S and VSD. Meanwhile, its reinforcement learning policy surpasses previous methods by 19% in success rate on OakInk-v2. Furthermore, DexMan can generate skills from both real and synthetic videos, without the need for manual data collection and costly motion capture, and enabling the creation of large-scale, diverse datasets for training generalist dexterous manipulation.
Read the full abstract
Computer Vision
Hierarchical Spatial Algorithms for High-Resolution Image Quantization and Feature Extraction
This study introduces a modular framework for spatial image processing, integrating grayscale quantization, color and brightness enhancement, image sharpening, bidirectional transformation pipelines, and geometric feature extraction. A stepwise intensity transformation quantizes grayscale images into eight discrete levels, producing a posterization effect that simplifies representation while preserving structural detail. Color enhancement is achieved via histogram equalization in both RGB and YCrCb color spaces, with the latter improving contrast while maintaining chrominance fidelity. Brightness adjustment is implemented through HSV value-channel manipulation, and image sharpening is performed using a 3 * 3 convolution kernel to enhance high-frequency details. A bidirectional transformation pipeline that integrates unsharp masking, gamma correction, and noise amplification achieved accuracy levels of 76.10% and 74.80% for the forward and reverse processes, respectively. Geometric feature extraction employed Canny edge detection, Hough-based line estimation (e.g., 51.50{\deg} for billiard cue alignment), Harris corner detection, and morphological window localization. Cue isolation further yielded 81.87% similarity against ground truth images. Experimental evaluation across diverse datasets demonstrates robust and deterministic performance, highlighting its potential for real-time image analysis and computer vision.
Read the full abstract
Computer Vision
Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
Visual Reinforcement Learning (RL) agents must learn to act based on high-dimensional image data where only a small fraction of the pixels is task-relevant. This forces agents to waste exploration and computational resources on irrelevant features, leading to sample-inefficient and unstable learning. To address this, inspired by human visual foveation, we introduce Gaze on the Prize. This framework augments visual RL with a learnable foveal attention mechanism (Gaze), guided by a self-supervised signal derived from the agent's experience pursuing higher returns (the Prize). Our key insight is that return differences reveal what matters most: If two similar representations produce different outcomes, their distinguishing features are likely task-relevant, and the gaze should focus on them accordingly. This is realized through return-guided contrastive learning that trains the attention to distinguish between the features relevant to success and failure. We group similar visual representations into positives and negatives based on their return differences and use the resulting labels to construct contrastive triplets. These triplets provide the training signal that teaches the attention mechanism to produce distinguishable representations for states associated with different outcomes. Our method achieves up to 2.52x improvement in sample efficiency and can solve challenging tasks from the ManiSkill3 benchmark that the baseline fails to learn, without modifying the underlying algorithm or hyperparameters.
Read the full abstract
Computer Vision
Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to infrastructure challenges in Jacobian-vector product (JVP) computation and the limitations of evaluation benchmarks like FID. This work represents the first effort to scale up continuous-time consistency to general application-level image and video diffusion models, and to make JVP-based distillation effective at large scale. We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks. Our investigation reveals fundamental quality limitations of sCM in fine-detail generation, which we attribute to error accumulation and the "mode-covering" nature of its forward-divergence objective. To remedy this, we propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer. This integration complements sCM with the "mode-seeking" reverse divergence, effectively improving visual quality while maintaining high generation diversity. Validated on large-scale models (Cosmos-Predict2, Wan2.1) up to 14B parameters and 5-second videos, rCM generally matches the state-of-the-art distillation method DMD2 on quality metrics while mitigating mode collapse and offering notable advantages in diversity, all without GAN tuning or extensive hyperparameter searches. The distilled models generate high-fidelity samples in only $1\sim4$ steps, accelerating diffusion sampling by $15\times\sim50\times$. These results position rCM as a practical and theoretically grounded framework for advancing large-scale diffusion distillation. Code is available at https://github.com/NVlabs/rcm.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
Reinforcing Diffusion Models by Direct Group Preference Optimization
While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic policy, yet the most cost-effective diffusion samplers are based on deterministic ODEs. Recent work addresses this issue by using inefficient SDE-based samplers to induce stochasticity, but this reliance on model-agnostic Gaussian noise leads to slow convergence. To resolve this conflict, we propose Direct Group Preference Optimization (DGPO), a new online RL algorithm that dispenses with the policy-gradient framework entirely. DGPO learns directly from group-level preferences, which utilize relative information of samples within groups. This design eliminates the need for inefficient stochastic policies, unlocking the use of efficient deterministic ODE samplers and faster training. Extensive results show that DGPO trains around 20 times faster than existing state-of-the-art methods and achieves superior performance on both in-domain and out-of-domain reward metrics. Code is available at https://github.com/Luo-Yihong/DGPO.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
Biology-driven assessment of deep learning super-resolution imaging of the porosity network in dentin
The mechanosensory system of teeth is currently believed to partly rely on Odontoblast cells stimulation by fluid flow through a porosity network extending through dentin. Visualizing the smallest sub-microscopic porosity vessels therefore requires the highest achievable resolution from confocal fluorescence microscopy, the current gold standard. This considerably limits the extent of the field of view to very small sample regions. To overcome this limitation, we tested different deep learning (DL) super-resolution (SR) models to allow faster experimental acquisitions of lower resolution images and restore optimal image quality by post-processing. Three supervised 2D SR models (RCAN, pix2pix, FSRCNN) and one unsupervised (CycleGAN) were applied to a unique set of experimentally paired high- and low-resolution confocal images acquired with different sampling schemes, resulting in a pixel size increase of x2, x4, x8. Model performance was quantified using a broad set of similarity and distribution-based image quality assessment (IQA) metrics, which yielded inconsistent results that mostly contradicted our visual perception. This raises the question of the relevance of such generic metrics to efficiently target the specific structure of dental porosity. To resolve this conflicting information, the generated SR images were segmented taking into account the specific scales and morphology of the porosity network and analysed by comparing connected components. Additionally, the capacity of the SR models to preserve 3D porosity connectivity throughout the confocal image stacks was evaluated using graph analysis. This biology-driven assessment allowed a far better mechanistic interpretation of SR performance, highlighting differences in model sensitivity to weak intensity features and the impact of non-linearity in image generation, which explains the failure of standard IQA metrics.
Read the full abstract
Computer Vision
VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?
The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making the existing benchmarks increasingly insufficient to evaluate state-of-the-art T2V models. First, current evaluation dimensions, such as per-frame aesthetic quality and temporal consistency, are no longer able to differentiate state-of-the-art T2V models. Second, event-level temporal causality-an essential property that differentiates videos from other modalities-remains largely unexplored. Third, existing benchmarks lack a systematic assessment of world knowledge, which are essential capabilities for building world models. To address these issues, we introduce VideoVerse, a comprehensive benchmark focusing on evaluating whether the current T2V model could understand complex temporal causality and world knowledge to synthesize videos. We collect representative videos across diverse domains and extract their event-level descriptions with inherent temporal causality, which are then rewritten into text-to-video prompts by independent annotators. For each prompt, we design ten evaluation dimensions covering dynamic and static properties, resulting in 300 prompts, 815 events, and 793 evaluation questions. Consequently, a human preference-aligned QA-based evaluation pipeline is developed by using modern vision-language models to systematically benchmark leading open- and closed-source T2V systems, revealing the current gap between T2V models and desired world modeling abilities.
Read the full abstract
Computer Vision · Cross-listed from cs.GR
Spectral Prefiltering of Neural Fields
Neural fields excel at representing continuous visual signals but typically operate at a single, fixed resolution. We present a simple yet powerful method to optimize neural fields that can be prefiltered in a single forward pass. Key innovations and features include: (1) We perform convolutional filtering in the input domain by analytically scaling Fourier feature embeddings with the filter's frequency response. (2) This closed-form modulation generalizes beyond Gaussian filtering and supports other parametric filters (Box and Lanczos) that are unseen at training time. (3) We train the neural field using single-sample Monte Carlo estimates of the filtered signal. Our method is fast during both training and inference, and imposes no additional constraints on the network architecture. We show quantitative and qualitative improvements over existing methods for neural-field filtering.
Read the full abstract
Computer Vision
Robust Source-Free Domain Adaptation for Medical Image Segmentation based on Curriculum Learning
Recent studies have uncovered a new research line, namely source-free domain adaptation, which adapts a model to target domains without using the source data. Such a setting can address the concerns on data privacy and security issues of medical images. However, current source-free domain adaptation frameworks mainly focus on the pseudo label refinement for target data without the consideration of learning procedure. Indeed, a progressive learning process from source to target domain will benefit the knowledge transfer during model adaptation. To this end, we propose a curriculum-based framework, namely learning from curriculum (LFC), for source-free domain adaptation, which consists of easy-to-hard and source-to-target curricula. Concretely, the former curriculum enables the framework to start learning with `easy' samples and gradually tune the optimization direction of model adaption by increasing the sample difficulty. While, the latter can stablize the adaptation process, which ensures smooth transfer of the model from the source domain to the target. We evaluate the proposed source-free domain adaptation approach on the public cross-domain datasets for fundus segmentation and polyp segmentation. The extensive experimental results show that our framework surpasses the existing approaches and achieves a new state-of-the-art.
Read the full abstract
Computer Vision
Detecting Legend Items on Historical Maps Using GPT-4o with In-Context Learning
Historical map legends are critical for interpreting cartographic symbols. However, their inconsistent layouts and unstructured formats make automatic extraction challenging. Prior work focuses primarily on segmentation or general optical character recognition (OCR), with few methods effectively matching legend symbols to their corresponding descriptions in a structured manner. We present a method that combines LayoutLMv3 for layout detection with GPT-4o using in-context learning to detect and link legend items and their descriptions via bounding box predictions. Our experiments show that GPT-4 with structured JSON prompts outperforms the baseline, achieving 88% F-1 and 85% IoU, and reveal how prompt design, example counts, and layout alignment affect performance. This approach supports scalable, layout-aware legend parsing and improves the indexing and searchability of historical maps across various visual styles.
Read the full abstract
Computer Vision
UniVideo: Unified Understanding, Generation, and Editing for Videos
Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design preserves the MLLM's original text generation capabilities, enables accurate interpretation of complex multimodal instructions, and maintains visual consistency in the generated content. Built on this architecture, UniVideo unifies diverse video generation and editing tasks under a single multimodal instruction paradigm and is jointly trained across them. Extensive experiments demonstrate that UniVideo matches or surpasses state-of-the-art task-specific baselines in text/image-to-video generation, in-context video generation and in-context video editing. Notably, the unified design of UniVideo enables two forms of generalization. First, UniVideo supports task composition, such as combining editing with style transfer, by integrating multiple capabilities within a single instruction. Second, even without explicit training on free-form video editing, UniVideo transfers its editing capability from large-scale image editing data to this setting, handling unseen instructions such as changing the environment or altering materials within a video. Beyond these core capabilities, UniVideo also supports visual-prompt-based video generation, where the MLLM interprets visual prompts and guides the MMDiT during synthesis. To foster future research, we released our model and code.
Read the full abstract
Computer Vision
Hyperspectral data augmentation with transformer-based diffusion models
The introduction of new generation hyperspectral satellite sensors, combined with advancements in deep learning methodologies, has significantly enhanced the ability to discriminate detailed land-cover classes at medium-large scales. However, a significant challenge in deep learning methods is the risk of overfitting when training networks with small labeled datasets. In this work, we propose a data augmentation technique that leverages a guided diffusion model. To effectively train the model with a limited number of labeled samples and to capture complex patterns in the data, we implement a lightweight transformer network. Additionally, we introduce a modified weighted loss function and an optimized cosine variance scheduler, which facilitate fast and effective training on small datasets. We evaluate the effectiveness of the proposed method on a forest classification task with 10 different forest types using hyperspectral images acquired by the PRISMA satellite. The results demonstrate that the proposed method outperforms other data augmentation techniques in both average and weighted average accuracy. The effectiveness of the method is further highlighted by the stable training behavior of the model, which addresses a common limitation in the practical application of deep generative models for data augmentation.
Read the full abstract
Computer Vision
SPICE: Simple and Practical Image Clarification and Enhancement
We introduce a simple and efficient method to enhance and clarify images. More specifically, we deal with low light image enhancement and clarification of hazy imagery (hazy/foggy images, images containing sand dust, and underwater images). Our method involves constructing an image filter to simulate low-light or hazy conditions and deriving approximate reverse filters to minimize distortions in the enhanced images. Experimental results show that our approach is highly competitive and often surpasses state-of-the-art techniques in handling extremely dark images and in enhancing hazy images. A key advantage of our approach lies in its simplicity: Our method is implementable with just a few lines of MATLAB code.
Read the full abstract
Computer Vision
Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
Vision-Language Models (VLMs) are becoming increasingly powerful, demonstrating strong performance on a variety of tasks that require both visual and textual understanding. Their strong generalisation abilities make them a promising component for automated driving systems, which must handle unexpected corner cases. However, to be trusted in such safety-critical applications, a model must first possess a reliable perception system. Moreover, since critical objects and agents in traffic scenes are often at a distance, we require systems that are not "shortsighted", i.e., systems with strong perception capabilities at both close (up to 20 meters) and long (30+ meters) range. With this in mind, we introduce Distance-Annotated Traffic Perception Question Answering (DTPQA), the first Visual Question Answering (VQA) benchmark focused solely on perception-based questions in traffic scenes, enriched with distance annotations. By excluding questions that require reasoning, we ensure that model performance reflects perception capabilities alone. Since automated driving hardware has limited processing power and cannot support large VLMs, our study centers on smaller VLMs. More specifically, we evaluate several state-of-the-art (SOTA) small VLMs on DTPQA and show that, despite the simplicity of the questions, these models significantly underperform compared to humans (~60% average accuracy for the best-performing small VLM versus ~85% human performance). However, it is important to note that the human sample size was relatively small, which imposes statistical limitations. We also identify specific perception tasks, such as distinguishing left from right, that remain particularly challenging for these models.
Read the full abstract
Computer Vision
LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation
Video diffusion models (DMs) have enabled high-quality video synthesis. However, their computation costs scale quadratically with sequence length because self-attention has quadratic complexity. While linear attention lowers the cost, fully replacing quadratic attention requires expensive pretraining due to the limited expressiveness of linear attention and the complexity of spatiotemporal modeling in video generation. In this paper, we present LinVideo, an efficient data-free post-training framework that replaces a target number of self-attention modules with linear attention while preserving the original model's performance. First, we observe a significant disparity in the replaceability of different layers. Instead of manual or heuristic choices, we frame layer selection as a binary classification problem and propose selective transfer, which automatically and progressively converts layers to linear attention with minimal performance impact. Additionally, to overcome the ineffectiveness and inefficiency of existing objectives for this transfer process, we introduce an anytime distribution matching (ADM) objective that aligns the distributions of samples across any timestep along the sampling trajectory. This objective is efficient and recovers model performance. Extensive experiments show that our method achieves a 1.25-2.00x speedup while preserving generation quality, and our 4-step distilled model further delivers a 15.92x latency reduction with minimal visual quality drop.
Read the full abstract
Computer Vision
Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge
Affordance segmentation aims to decompose 3D objects into parts that serve distinct functional roles, enabling models to reason about object interactions rather than mere recognition. Existing methods, mostly following the paradigm of 3D semantic segmentation or prompt-based frameworks, struggle when geometric cues are weak or ambiguous, as sparse point clouds provide limited functional information. To overcome this limitation, we leverage the rich semantic knowledge embedded in large-scale 2D Vision Foundation Models (VFMs) to guide 3D representation learning through a cross-modal alignment mechanism. Specifically, we propose Cross-Modal Affinity Transfer (CMAT), a pretraining strategy that compels the 3D encoder to align with the semantic structures induced by lifted 2D features. CMAT is driven by a core affinity alignment objective, supported by two auxiliary losses, geometric reconstruction and feature diversity, which together encourage structured and discriminative feature learning. Built upon the CMAT-pretrained backbone, we employ a lightweight affordance segmentor that injects text or visual prompts into the learned 3D space through an efficient cross-attention interface, enabling dense and prompt-aware affordance prediction while preserving the semantic organization established during pretraining. Extensive experiments demonstrate consistent improvements over previous state-of-the-art methods in both accuracy and efficiency.
Read the full abstract
Computer Vision
LTCA: Long-range Temporal Context Attention for Referring Video Object Segmentation
Referring Video Segmentation (RVOS) aims to segment objects in videos given linguistic expressions. The key to solving RVOS is to extract long-range temporal context information from the interactions of expressions and videos to depict the dynamic attributes of each object. Previous works either adopt attention across all the frames or stack dense local attention to achieve a global view of temporal context. However, they fail to strike a good balance between locality and globality, and the computation complexity significantly increases with the increase of video length. In this paper, we propose an effective long-range temporal context attention (LTCA) mechanism to aggregate global context information into object features. Specifically, we aggregate the global context information from two aspects. Firstly, we stack sparse local attentions to balance the locality and globality. We design a dilated window attention across frames to aggregate local context information and perform such attention in a stack of layers to enable a global view. Further, we enable each query to attend to a small group of keys randomly selected from a global pool to enhance the globality. Secondly, we design a global query to interact with all the other queries to directly encode the global context information. Experiments show our method achieves new state-of-the-art on four referring video segmentation benchmarks. Notably, our method shows an improvement of 11.3% and 8.3% on the MeViS valu and val datasets respectively.
Read the full abstract
Computer Vision
Learning Neural Exposure Fields for View Synthesis
Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and view synthesis. Despite achieving high-quality results for common benchmarks with curated data, outputs often degrade for data that contain per image variations such as strong exposure changes, present, e.g., in most scenes with indoor and outdoor areas or rooms with windows. In this paper, we introduce Neural Exposure Fields (NExF), a novel technique for robustly reconstructing 3D scenes with high quality and 3D-consistent appearance from challenging real-world captures. In the core, we propose to learn a neural field predicting an optimal exposure value per 3D point, enabling us to optimize exposure along with the neural scene representation. While capture devices such as cameras select optimal exposure per image/pixel, we generalize this concept and perform optimization in 3D instead. This enables accurate view synthesis in high dynamic range scenarios, bypassing the need of post-processing steps or multi-exposure captures. Our contributions include a novel neural representation for exposure prediction, a system for joint optimization of the scene representation and the exposure field via a novel neural conditioning mechanism, and demonstrated superior performance on challenging real-world data. We find that our approach trains faster than prior works and produces state-of-the-art results on several benchmarks improving by over 55% over best-performing baselines.
Read the full abstract
Computer Vision
A Multimodal Depth-Aware Method For Embodied Reference Understanding
Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues. While prior works have shown progress in open-vocabulary object detection, they often fail in ambiguous scenarios where multiple candidate objects exist in the scene. To address these challenges, we propose a novel ERU framework that jointly leverages LLM-based data augmentation, depth-map modality, and a depth-aware decision module. This design enables robust integration of linguistic and embodied cues, improving disambiguation in complex or cluttered environments. Experimental results on two datasets demonstrate that our approach significantly outperforms existing baselines, achieving more accurate and reliable referent detection.
Read the full abstract
Computer Vision
One Stone with Two Birds: A Null-Text-Null Frequency-Aware Diffusion Models for Text-Guided Image Inpainting
Text-guided image inpainting aims at reconstructing the masked regions as per text prompts, where the longstanding challenges lie in the preservation for unmasked regions, while achieving the semantics consistency between unmasked and inpainted masked regions. Previous arts failed to address both of them, always with either of them to be remedied. Such facts, as we observed, stem from the entanglement of the hybrid (e.g., mid-and-low) frequency bands that encode varied image properties, which exhibit different robustness to text prompts during the denoising process. In this paper, we propose a null-text-null frequency-aware diffusion models, dubbed NTN-Diff, for text-guided image inpainting, by decomposing the semantics consistency across masked and unmasked regions into the consistencies as per each frequency band, while preserving the unmasked regions, to circumvent two challenges in a row. Based on the diffusion process, we further divide the denoising process into early (high-level noise) and late (low-level noise) stages, where the mid-and-low frequency bands are disentangled during the denoising process. As observed, the stable mid-frequency band is progressively denoised to be semantically aligned during text-guided denoising process, which, meanwhile, serves as the guidance to the null-text denoising process to denoise low-frequency band for the masked regions, followed by a subsequent text-guided denoising process at late stage, to achieve the semantics consistency for mid-and-low frequency bands across masked and unmasked regions, while preserve the unmasked regions. Extensive experiments validate the superiority of NTN-Diff over the state-of-the-art diffusion models to text-guided diffusion models. Our code can be accessed from https://github.com/htyjers/NTN-Diff.
Read the full abstract
Computer Vision · Cross-listed from cs.GR
SViM3D: Stable Video Material Diffusion for Single Image 3D Generation
We present Stable Video Materials 3D (SViM3D), a framework to predict multi-view consistent physically based rendering (PBR) materials, given a single image. Recently, video diffusion models have been successfully used to reconstruct 3D objects from a single image efficiently. However, reflectance is still represented by simple material models or needs to be estimated in additional steps to enable relighting and controlled appearance edits. We extend a latent video diffusion model to output spatially varying PBR parameters and surface normals jointly with each generated view based on explicit camera control. This unique setup allows for relighting and generating a 3D asset using our model as neural prior. We introduce various mechanisms to this pipeline that improve quality in this ill-posed setting. We show state-of-the-art relighting and novel view synthesis performance on multiple object-centric datasets. Our method generalizes to diverse inputs, enabling the generation of relightable 3D assets useful in AR/VR, movies, games and other visual media.
Read the full abstract
Computer Vision
Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classification
Multi-label classification (MLC) offers a more comprehensive semantic understanding of Remote Sensing (RS) imagery compared to traditional single-label classification (SLC). However, obtaining complete annotations for MLC is particularly challenging due to the complexity and high cost of the labeling process. As a practical alternative, single-positive multi-label learning (SPML) has emerged, where each image is annotated with only one relevant label, and the model is expected to recover the full set of labels. While scalable, SPML introduces significant supervision ambiguity, demanding specialized solutions for model training. Although various SPML methods have been proposed in the computer vision domain, research in the RS context remains limited. To bridge this gap, we propose Adaptive Gradient Calibration (AdaGC), a novel and generalizable SPML framework tailored to RS imagery. AdaGC adopts a gradient calibration (GC) mechanism with a dual exponential moving average (EMA) module for robust pseudo-label generation. We introduce a theoretically grounded, training-dynamics-based indicator to adaptively trigger GC, which ensures GC's effectiveness by preventing it from being affected by model underfitting or overfitting to label noise. Extensive experiments on two benchmark RS datasets under two distinct label noise types demonstrate that AdaGC achieves state-of-the-art (SOTA) performance while maintaining strong robustness across diverse settings. The codes and data will be released at https://github.com/rslab-unitrento/AdaGC.
Read the full abstract
Computer Vision
Fine-grained text-driven dual-human motion generation via dynamic hierarchical interaction
Human interaction is inherently dynamic and hierarchical, where the dynamic refers to the motion changes with distance, and the hierarchy is from individual to inter-individual and ultimately to overall motion. Exploiting these properties is vital for dual-human motion generation, while existing methods almost model human interaction temporally invariantly, ignoring distance and hierarchy. To address it, we propose a fine-grained dual-human motion generation method, namely FineDual, a tri-stage method to model the dynamic hierarchical interaction from individual to inter-individual. The first stage, Self-Learning Stage, divides the dual-human overall text into individual texts through a Large Language Model, aligning text features and motion features at the individual level. The second stage, Adaptive Adjustment Stage, predicts interaction distance by an interaction distance predictor, modeling human interactions dynamically at the inter-individual level by an interaction-aware graph network. The last stage, Teacher-Guided Refinement Stage, utilizes overall text features as guidance to refine motion features at the overall level, generating fine-grained and high-quality dual-human motion. Extensive quantitative and qualitative evaluations on dual-human motion datasets demonstrate that our proposed FineDual outperforms existing approaches, effectively modeling dynamic hierarchical human interaction.
Read the full abstract
Computer Vision
InstructUDrag: Joint Text Instructions and Object Dragging for Interactive Image Editing
Text-to-image diffusion models have shown great potential for image editing, with techniques such as text-based and object-dragging methods emerging as key approaches. However, each of these methods has inherent limitations: text-based methods struggle with precise object positioning, while object dragging methods are confined to static relocation. To address these issues, we propose InstructUDrag, a diffusion-based framework that combines text instructions with object dragging, enabling simultaneous object dragging and text-based image editing. Our framework treats object dragging as an image reconstruction process, divided into two synergistic branches. The moving-reconstruction branch utilizes energy-based gradient guidance to move objects accurately, refining cross-attention maps to enhance relocation precision. The text-driven editing branch shares gradient signals with the reconstruction branch, ensuring consistent transformations and allowing fine-grained control over object attributes. We also employ DDPM inversion and inject prior information into noise maps to preserve the structure of moved objects. Extensive experiments demonstrate that InstructUDrag facilitates flexible, high-fidelity image editing, offering both precision in object relocation and semantic control over image content.