ICCV 2025 Papers

The intrication of brain signals drives research that leverages multimodal AI to align brain modalities with visual and textual data for explainable descriptions. However, most existing studies are limited to coarse interpretations, lacking essential details on object descriptions, locations, attributes, and their relationships. This leads to imprecise and ambiguous reconstructions when using such cues for visual decoding. To address this, we analyze different choices of vision feature spaces from pre-trained visual components within Multimodal Large Language Models (MLLMs) and introduce a zero-shot multimodal brain decoding method that interacts with these models to decode across multiple levels of granularities. To assess a model's ability to decode fine details from brain signals, we propose the Multi-Granularity Brain Detail Understanding Benchmark (MG-BrainDub). This benchmark includes two key tasks: detailed descriptions and salient question-answering, with metrics highlighting key visual elements like objects, attributes, and relationships. Our approach enhances neural decoding precision and supports more accurate neuro-decoding applications.

Domain Generalized Semantic Segmentation (DGSS) is a critical yet challenging task, as domain shifts in unseen environments can severely compromise model performance. While recent studies enhance feature alignment by projecting features into the source domain, they often neglect intrinsic latent domain priors, leading to suboptimal results. In this paper, we introduce PDAF, a Probabilistic Diffusion Alignment Framework that enhances the generalization of existing segmentation networks through probabilistic diffusion modeling. PDAF introduces a Latent Domain Prior (LDP) to capture domain shifts and uses this prior as a conditioning factor to align both source and unseen target domains. To achieve this, PDAF integrates into a pre-trained segmentation model and utilizes paired source and pseudo-target images to simulate latent domain shifts, enabling LDP modeling. The framework comprises three modules: the Latent Prior Extractor (LPE) predicts the LDP by supervising domain shifts; the Domain Compensation Module (DCM) adjusts feature representations to mitigate domain shifts; and the Diffusion Prior Estimator (DPE) leverages a diffusion process to estimate the LDP without requiring paired samples. This design enables PDAF to iteratively model domain shifts, progressively refining feature representations to enhance generalization under complex target conditions. Extensive experiments validate the effectiveness of PDAF across diverse and challenging urban scenes.

Transformer-based diffusion models have recently superseded traditional U-Net architectures, with multimodal diffusion transformers (MM-DiT) emerging as the dominant approach in state-of-the-art models like Stable Diffusion 3 and Flux.1. Previous approaches have relied on unidirectional cross-attention mechanisms, with information flowing from text embeddings to image latents. In contrast, MM-DiT introduces a unified attention mechanism that concatenates input projections from both modalities and performs a single full attention operation, allowing bidirectional information flow between text and image branches. This architectural shift presents significant challenges for existing editing techniques. In this paper, we systematically analyze MM-DiT's attention mechanism by decomposing attention matrices into four distinct blocks, revealing their inherent characteristics. Through these analyses, we propose a robust, prompt-based image editing method for MM-DiT that supports global to local edits across various MM-DiT variants, including few-step models. We believe our findings bridge the gap between existing U-Net-based methods and emerging architectures, offering deeper insights into MM-DiT's behavioral patterns.

Recent advances in novel view synthesis (NVS) have enabled real-time rendering with 3D Gaussian Splatting (3DGS). However, existing methods struggle with artifacts and missing regions when rendering unseen viewpoints, limiting seamless scene exploration. To address this, we propose a 3DGS-based pipeline that generates additional training views to enhance reconstruction. We introduce an information-gain-driven virtual camera placement strategy to maximize scene coverage, followed by video diffusion priors to refine rendered results. Fine-tuning 3D Gaussians with these enhanced views significantly improves reconstruction quality. To evaluate our method, we present Wild-Explore, a benchmark designed for challenging scene exploration. Experiments demonstrate that our approach outperforms existing 3DGS-based methods, enabling high-quality, artifact-free rendering from arbitrary viewpoints.

Out-of-distribution (OOD) detection in 3D point cloud data remains a challenge, particularly in applications where safe and robust perception is critical. While existing OOD detection methods have shown progress for 2D image data, extending these to 3D environments involves unique obstacles. This paper introduces a training-free framework that leverages Vision-Language Models (VLMs) for effective OOD detection in 3D point clouds. By constructing a graph based on class prototypes and testing data, we exploit the data manifold structure to enhancing the effectiveness of VLMs for 3D OOD detection. We propose a novel Graph Score Propagation (GSP) method that incorporates prompt clustering and self-training negative prompting to improve OOD scoring with VLM. Our method is also adaptable to few-shot scenarios, providing options for practical applications. We demonstrate that GSP consistently outperforms state-of-the-art methods across synthetic and real-world datasets for 3D point cloud OOD detection.

Recent domain generalized semantic segmentation (DGSS) studies have achieved notable improvements by distilling semantic knowledge from Vision-Language Models (VLMs). However, they overlook the semantic misalignment between visual and textual contexts, which arises due to the rigidity of a fixed context prompt learned on a single source domain. To this end, we present a novel domain generalization framework for semantic segmentation, namely Domain-aware Prompt-driven Masked Transformer (DPMFormer). Firstly, we introduce domain-aware prompt learning to facilitate semantic alignment between visual and textual cues. To capture various domain-specific properties with a single source dataset, we propose domain-aware contrastive learning along with the texture perturbation that diversifies the observable domains. Lastly, to establish a framework resilient against diverse environmental changes, we have proposed the domain-robust consistency learning which guides the model to minimize discrepancies of prediction from original and the augmented images. Through experiments and analyses, we demonstrate the superiority of the proposed framework, which establishes a new state-of-the-art on various DGSS benchmarks.

Task-driven image restoration (TDIR) has recently emerged to address performance drops in high-level vision tasks caused by low-quality (LQ) inputs. Previous TDIR methods struggle to handle practical scenarios in which images are degraded by multiple complex factors, leaving minimal clues for restoration. This motivates us to leverage the diffusion prior, one of the most powerful natural image priors. However, while the diffusion prior can help generate visually plausible results, using it to restore task-relevant details remains challenging, even when combined with recent TDIR methods. To address this, we propose EDTR, which effectively harnesses the power of diffusion prior to restore task-relevant details. Specifically, we propose directly leveraging useful clues from LQ images in the diffusion process by generating from pixel-error-based pre-restored LQ images with mild noise added. Moreover, we employ a small number of denoising steps to prevent the generation of redundant details that dilute crucial task-related information. We demonstrate that our method effectively utilizes diffusion prior for TDIR, significantly enhancing task performance and visual quality across diverse tasks with multiple complex degradations.

"What cannot be measured cannot be improved" while likely never uttered by Lord Kelvin, summarizes effectively the driving force behind this work. This paper presents a detailed discussion of automated metrics for evaluating structured 3D reconstructions. Pitfalls of each metric are discussed, and an analysis through the lens of expert 3D modelers' preferences is presented. A set of systematic "unit tests" are proposed to empirically verify desirable properties, and context aware recommendations regarding which metric to use depending on application are provided. Finally, a learned metric distilled from human expert judgments is proposed and analyzed. The source code is available at https://github.com/s23dr/ wireframe-metrics-iccv2025.

Generating text descriptions of objects in 3D indoor scenes is an important building block of embodied understanding. Existing methods do this by describing objects at a single level of detail, which often does not capture fine-grained details such as varying textures, materials, and shapes of the parts of objects.We propose the task of expressive 3D captioning: given an input 3D scene, describe objects at multiple levels of detail: a high-level object description, and a low-level description of the properties of its parts.To produce such captions, we present ExCap3D, an expressive 3D captioning model which takes as input a 3D scan, and for each detected object in the scan, generates a fine-grained collective description of the parts of the object, along with an object-level description conditioned on the part-level description.We design ExCap3D to encourage semantic consistency between the generated text descriptions, as well as textual similarity in the latent space, to further increase the quality of the generated captions.To enable this task, we generated the ExCap3D Dataset by leveraging a visual-language model (VLM) for multi-view captioning. ExCap3D Dataset contains captions on the ScanNet++ dataset with varying levels of detail,comprising 190k text descriptions of 34k 3D objects in 947 indoor scenes.Our experiments show that the object- and part-level of detail captions generated by ExCap3D are of higher quality than those produced by state-of-the-art methods, with a Cider score improvement of 17% and 126% for object- and part-level details respectively. Our code, dataset and models will be made publicly available.

Dexterous robotic hands often struggle to generalize effectively in complex environments due to models trained on low-diversity data. However, the real world presents an inherently unbounded range of scenarios. A natural solution is to enable robots learning from experience in complex environments--an approach akin to evolution, where systems improve through learning from both failures and successes. Motivated by this, we propose EvolvingGrasp, an evolutionary grasp generation method that continuously enhances grasping performance through efficient preference alignment. Specifically, we introduce Handpose-wise Preference Optimization (HPO), which allows the model to continuously align with preferences from both positive and negative feedback while progressively refining its grasping strategies. To further enhance efficiency and reliability during online adjustments, we incorporate a Physics-aware Consistency Model within HPO, which accelerates inference, reduces the number of timesteps needed for preference fine-tuning, and ensures physical plausibility throughout the process. Our results validate that EvolvingGrasp enables evolutionary grasp generation, ensuring robust, physically feasible, and preference-aligned grasping in both simulation and real scenarios.

Existing logit-based knowledge distillation methods typically employ singularly deterministic categorical distributions, which eliminates the inherent uncertainty in network predictions and thereby limiting the effective transfer of knowledge. To address this limitation, we introduce distribution-based probabilistic modeling as a more comprehensive representation of network knowledge. Specifically, we regard the categorical distribution as a random variable and leverage deep neural networks to predict its distribution, representing it as an evidential second-order distribution. Based on the second-oder modeling, we propose Evidential Knowledge Distillation (EKD) which distills both the expectation of the teacher distribution and the distribution itself into the student. The expectation captures the macroscopic characteristics of the distribution, while the distribution itself conveys microscopic information about the classification boundaries. Additionally, we theoretically show that EKD's distillation objective provides an upper bound on the student's expected risk when treating the teacher's predictions as ground truth. Extensive experiments on several standard benchmarks across various teacher-student network pairs highlight the effectiveness and superior performance of EKD. Our code is available at https://github.com/lyxiang-casia/EKD.

Multimodal learning, which involves integrating information from various modalities such as text, images, audio, and video, is pivotal for numerous complex tasks like visual question answering, cross-modal retrieval, and caption generation. Traditional approaches rely on modality-specific encoders and late fusion techniques, which can hinder flexibility when adapting to new tasks or modalities. To address these limitations, we introduce a novel framework that extends the concept of task reformulation beyond natural language processing (NLP) to multimodal learning. We propose to reformulate diverse multimodal tasks into a unified next-frame prediction problem, allowing a single model to handle different modalities without modality-specific components. This method treats all inputs and outputs as sequential frames in a video, enabling seamless integration of modalities and effective knowledge transfer across tasks. Our approach is evaluated on a range of tasks, including text-to-text, image-to-text, video-to-text, and audio-to-text, demonstrating the model's ability to generalize across modalities with minimal adaptation. We show that task reformulation can significantly simplify multimodal model design across various tasks, laying the groundwork for more generalized multimodal foundation models.

We present EventUPS, the first uncalibrated photometric stereo (UPS) method using an event camera--a neuromorphic sensor that asynchronously detects brightness changes with microsecond resolution. Traditional frame-based UPS methods are hindered by high bandwidth demands and limited use in dynamic scenes. These methods require dense image correspondence under varying illumination and are incompatible with the fundamentally different sensing paradigm of event data. Our approach introduces three key innovations: an augmented null space formulation that directly relates each event to joint constraints on surface normals and lighting, naturally handling ambient illumination; a continuous parameterization of time-varying illumination that connects asynchronous events to synchronized lighting estimation; and a lighting fixture with known relative geometry that reduces ambiguity to a convex-concave uncertainty. We validate EventUPS using a custom-built LED lighting system. Experimental results show that our method achieves accuracy surpassing its frame-based counterpart while requiring only 5% of the data bandwidth.

In low-light environments, longer exposure times are commonly used to enhance image visibility; however, this inevitably leads to motion blur. Even with a long exposure time, videos captured in low-light environments still suffer from issues such as low visibility, low contrast, and color distortion. Additionally, the long exposure time results in videos with a low frame rate. Therefore, videos captured in low-light exhibit low visibility and motion blur, as well as low frame rates. To overcome these limitations, we propose a novel problem aimed at transforming motion-blurred, low-frame-rate videos with poor visibility in low-light environments into high-frame-rate videos while simultaneously enhancing their visibility. To tackle this challenge, we leverage the unique advantages of event cameras, which capture scene changes asynchronously, providing superior temporal resolution and a wider dynamic range compared to conventional frame-based cameras. These properties make event cameras particularly effective in reducing motion blur, compensating for low frame rates, and enhancing visibility in low-light conditions. To this end, we developed a hybrid camera system that integrates two RGB cameras and an event camera, capturing a dedicated dataset for this task and proposing novel network architectures to effectively address this problem. The project pages are available at https://sites.google.com/view/eledi-iccv.

Events provide High Dynamic Range (HDR) intensity change which can guide Low Dynamic Range (LDR) image for HDR reconstruction. However, events only provide temporal intensity differences and it is still ill-posed in over-/under-exposed areas due to missing initial reference brightness and color information. With strong generation ability, diffusion models have shown their potential for tackling ill-posed problems. Therefore, we introduce conditional diffusion models to hallucinate missing information. Whereas, directly adopting events and LDR image as conditions is complicated for diffusion models to sufficiently utilize their information. Thus we introduce a pretrained events-image encoder tailored for HDR reconstruction and a pyramid fusion module to provide HDR conditions, which can be efficiently and effectively utilized by the diffusion model. Moreover, the generation results of diffusion models usually exhibit distortion, particularly for fine-grained details. To better preserve fidelity and suppress distortion, we propose a fine-grained detail recovery approach using a histogram-based structural loss. Experiments on real and synthetic data show the effectiveness of the proposed method in terms of both detail preservation and information hallucination.

Deformable 3D Gaussian Splatting (3D-GS) is limited by missing intermediate motion information due to the low temporal resolution of RGB cameras. To address this, we introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction. We observe that threshold modeling for events plays a crucial role in achieving high-quality reconstruction. Therefore, we propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling. Moreover, we introduce a Dynamic-Static Decomposition strategy that first identifies dynamic areas by exploiting the inability of static Gaussians to represent motions, then applies a buffer-based soft decomposition to separate dynamic and static areas. This strategy accelerates rendering by avoiding unnecessary deformation in static areas, and focuses on dynamic areas to enhance fidelity. Additionally, we contribute the first event-inclusive 4D benchmark with synthetic and real-world dynamic scenes, on which our method achieves state-of-the-art performance.

Visual vibrometry has emerged as a powerful technique for remote acquisition of audio and the physical properties of materials. To capture high-frequency vibrations, frame-based approaches often require a high-speed video camera and bright lighting to compensate for the short exposure time. In this paper, we introduce event-based visual vibrometry, a new high-speed visual vibration sensing method using an event camera. By leveraging the high temporal resolution and low bandwidth characteristics of event cameras, event-based visual vibrometry enables high-speed vibration sensing under ambient lighting conditions with improved data efficiency. Specifically, we leverage a hybrid camera system and propose an event-based subtle motion estimation framework that integrates an optimization-based approach based on the event generation model and a motion refinement network. We demonstrate our method by capturing vibration caused by audio sources and estimating material properties for various objects.

Small object detection (SOD) in anti-UAV task is a challenging problem due to the small size of UAVs and complex backgrounds. Traditional frame-based cameras struggle to detect small objects in complex environments due to their low frame rates, limited dynamic range, and data redundancy. Event cameras, with microsecond temporal resolution and high dynamic range, provide a more effective solution for SOD. However, existing event-based object detection datasets are limited in scale, feature large targets size, and lack diverse backgrounds, making them unsuitable for SOD benchmarks. In this paper, we introduce a Event-based Small object detection (EVSOD) dataset (namely EV-UAV), the first large-scale, highly diverse benchmark for anti-UAV tasks. It includes 147 sequences with over 2.3 million event-level annotations, featuring extremely small targets (averaging 6.8 x 5.4 pixels) and diverse scenarios such as urban clutter and extreme lighting conditions. Furthermore, based on the observation that small moving targets form continuous curves in spatiotemporal event point clouds, we propose Event based Sparse Segmentation Network (EV-SpSegNet), a novel baseline for event segmentation in point cloud space, along with a Spatiotemporal Correlation (STC) loss that leverages motion continuity to guide the network in retaining target events. Extensive experiments on the EV-UAV dataset demonstrate the superiority of our method and provide a benchmark for future research in EVSOD.