ICCV 2025 Papers

We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that facilitates bidirectional information exchange between video and audio diffusion models through temporally-aligned self-attention operations. Unlike prior work that uses dedicated models for A2V and V2A tasks and relies on pretrained feature extractors, AV-Link achieves both tasks in a single self-contained framework, directly leveraging features obtained by the complementary modality (i.e. video features to generate audio, or audio features to generate video). Extensive evaluations demonstrate that AV-Link achieves substantial improvements in audio-video synchronization, outperforming more expensive baselines such as MovieGen V2A model.

We introduce AV-Flow, an audio-visual generative model that animates photo-realistic 4D talking avatars given only text input. In contrast to prior work that assumes an existing speech signal, we synthesize speech and vision jointly. We demonstrate human-like speech synthesis, synchronized lip motion, lively facial expressions and head pose; all generated from just text characters. The core premise of our approach lies in the architecture of our two parallel diffusion transformers. Intermediate highway connections ensure communication between the audio and visual modalities, and thus, synchronized speech intonation and facial dynamics (e.g., eyebrow motion). Our model is trained with flow matching, leading to expressive results and fast inference. In case of dyadic conversations, AV-Flow produces an always-on avatar, that actively listens and reacts to the audio-visual input of a user. Through extensive experiments, we show that our method outperforms prior work, synthesizing natural-looking 4D talking avatars.

Recent advancements in reasoning optimization have greatly enhanced the performance of large language models (LLMs). However, existing work fails to address the complexities of audio-visual scenarios, underscoring the need for further research. In this paper, we introduce AURELIA, a novel actor-critic based audio-visual (AV) reasoning framework that distils structured, step-by-step reasoning into AVLLMs at test time, improving their ability to process complex multi-modal inputs without additional training or fine-tuning. To further advance AVLLM reasoning skills, we present AVReasonBench, a challenging benchmark comprising 4500 audio-visual questions, each paired with detailed step-by-step reasoning. Our benchmark spans six distinct tasks, including AV-GeoIQ, which evaluates AV reasoning combined with geographical and cultural knowledge. Evaluating 18 AVLLMs on AVReasonBench reveals significant limitations in their multi-modal reasoning capabilities. Using AURELIA, we achieve up to a 100% relative improvement, demonstrating its effectiveness. This performance gain highlights the potential of reasoning-enhanced data generation for advancing AVLLMs in real-world applications.

While 3D facial animation has made impressive progress, challenges still exist in realizing fine-grained stylized 3D facial expression manipulation due to the lack of appropriate datasets. In this paper, we introduce the AUBlendSet, a 3D facial dataset based on AU-Blendshape representation for fine-grained facial expression manipulation across identities. AUBlendSet is a blendshape data collection based on 32 standard facial action units (AUs) across 500 identities, along with an additional set of facial postures annotated with detailed AUs. Based on AUBlendSet, we propose AUBlendNet to learn AU-Blendshape basis vectors for different character styles. AUBlendNet predicts, in parallel, the AU-Blendshape basis vectors of the corresponding style for a given identity mesh, thereby achieving stylized 3D emotional facial manipulation. We comprehensively validate the effectiveness of AUBlendSet and AUBlendNet through tasks such as stylized facial expression manipulation, speech-driven emotional facial animation, and emotion recognition data augmentation. Through a series of qualitative and quantitative experiments, we demonstrate the potential and importance of AUBlendSet and AUBlendNet in 3D facial animation tasks. To the best of our knowledge, AUBlendSet is the first dataset, and AUBlendNet is the first network for continuous 3D facial expression manipulation for any identity through facial AUs. Our source code is available at https://github.com/wslh852/AUBlendNet.git.

Parametric body models offer expressive 3D representation of humans across a wide range of poses, shapes, and facial expressions, typically derived by learning a basis over registered 3D meshes. However, existing human mesh modeling approaches struggle to capture detailed variations across diverse body poses and shapes, largely due to limited training data diversity and restrictive modeling assumptions. Moreover, the common paradigm first optimizes the external body surface using a linear basis, then regresses internal skeletal joints from surface vertices. This approach introduces problematic dependencies between internal skeleton and outer soft tissue, limiting direct control over body height and bone lengths. To address these issues, we present ATLAS, a high-fidelity body model learned from 600k high-resolution scans captured using 240 synchronized cameras. Unlike previous methods, we explicitly decouple the shape and skeleton bases by grounding our mesh representation in the human skeleton. This decoupling enables enhanced shape expressivity, fine-grained customization of body attributes, and keypoint fitting independent of external soft-tissue characteristics. ATLAS outperforms existing methods by fitting unseen subjects in diverse poses more accurately, and quantitative evaluations show that our non-linear pose correctives more effectively capture complex poses compared to linear models.

Vision-language tracking aims to locate the target object in the video sequence using a template patch and a language description provided in the initial frame. To achieve robust tracking, especially in complex long-term scenarios that reflect real-world conditions as recently highlighted by MGIT, it is essential not only to characterize the target features but also to utilize the context features related to the target. However, the visual and textual target-context cues derived from the initial prompts generally align only with the initial target state. Due to their dynamic nature, target states are constantly changing, particularly in complex long-term sequences. It is intractable for these cues to continuously guide Vision-Language Trackers (VLTs). Furthermore, for the text prompts with diverse expressions, our experiments reveal that existing VLTs struggle to discern which words pertain to the target or the context, complicating the utilization of textual cues. In this work, we present a novel tracker named ATCTrack, which can obtain multimodal cues Aligned with the dynamic target states through comprehensive Target-Context feature modeling, thereby achieving robust tracking. Specifically, (1) for the visual modality, we propose an effective temporal visual target-context modeling approach that provides the tracker with timely visual cues. (2) For the textual modality, we achieve precise target words identification solely based on textual content, and design an innovative context words calibration method to adaptively utilize auxiliary context words. (3) We conduct extensive experiments on mainstream benchmarks and ATCTrack achieves a new SOTA performance. The code and models will be released at: https://github.com/XiaokunFeng/ATCTrack.

Vision-language models such as CLIP have recently propelled open-vocabulary dense prediction tasks by enabling recognition of a broad range of visual concepts. However, CLIP still struggles with fine-grained, region-level understanding, hindering its effectiveness on these dense prediction tasks. We identify two pivotal factors required to address this limitation: semantic coherence and fine-grained vision-language alignment. Current adaptation methods often improve fine-grained alignment at the expense of semantic coherence, and often rely on extra modules or supervised fine-tuning. To overcome these issues, we propose Any-to-Any Self-Distillation (ATAS), a novel approach that simultaneously enhances semantic coherence and fine-grained alignment by leveraging a model's own knowledge across all representation levels. Unlike prior methods, ATAS uses only unlabeled images and an internal self-distillation process to refine CLIP's representations, preserving local semantic consistency while sharpening local detail recognition. On open-vocabulary object detection and semantic segmentation benchmarks, ATAS achieves substantial performance gains, outperforming baseline CLIP models. These results validate the effectiveness of our approach and underscore the importance of jointly maintaining semantic coherence and fine-grained alignment for advanced open-vocabulary dense prediction.

Albeit existing Single-Domain Generalized Object Detection (Single-DGOD) methods enable models to generalize to unseen domains, most assume that the training and testing data share the same label space. In real-world scenarios, unseen domains often introduce previously unknown objects, a challenge that has been largely overlooked. In this paper, we tackle the practical problem of Single-domain Generalizable Open-Set Object Detection (SG-OSOD), which addresses both unseen domains and unknown classes. We identify two key challenges: (1) detecting unknown classes with only known-class data, and (2) learning robust features to mitigate domain shift. To address these challenges, we propose the framework termed \texttt ASGS , which leverages adaptive subgraph structures to enhance the understanding of unknown scenes and classes. \texttt ASGS consists of Subgraph-wise Unknown-class Learning (SUL) and Class-wise Embedding Compaction (CEC). SUL employs non-parametric methods to detect unknown samples and performs Adaptive Subgraph Searching (ASS) for high-order structural feature extraction, enabling domain-robust unknown class learning. Moreover, the CEC module enhances class discrimination robustness through contrastive learning, which results in more compact class clusters in unknown scenarios. Experimental results demonstrate the effectiveness of the proposed \texttt ASGS .

We propose ASCENT, a novel framework for tracking neurons in 3D fluorescence microscopy recordings without relying on manual track annotations. ASCENT leverages self-supervised contrastive learning to learn robust, discriminative embeddings from detected neuron candidates. At its core is a volume compression module that transforms full 3D volumetric data into an efficient 2D representation by iteratively projecting along the z-axis and integrating positional information. This compressed representation is processed by a deep encoder (e.g., ResNet or Vision Transformer) to yield robust feature vectors that capture both appearance and spatial relationships among neurons. Extensive experiments on both in-house and public datasets demonstrate that ASCENT achieves state-of-the-art tracking performance with fast inference speed while removing the need for costly manual labeling and heavy pre- and post-processing. Our results suggest that this approach provides a scalable solution for 3D neuron tracking and holds promise for applications such as inter-individual neuron identity matching and demixing overlapping cells.

Visual relation detection (VRD) is the task of identifying the relationships between objects in a scene. VRD models trained solely on relation detection data struggle to generalize beyond the relations on which they are trained. While prompt tuning has been used to adapt vision-language models (VLMs) for VRD, it uses handcrafted prompts and struggles with novel or complex relations. We argue that instruction tuning offers a more effective solution by fine-tuning VLMs on diverse instructional data. We thus introduce ART, an Adaptive Relation Tuning framework that adapts VLMs for VRD through instruction tuning and strategic instance selection. By converting VRD datasets into an instruction-tuning format and employing an adaptive sampling algorithm, ART directs the VLM to focus on informative relations while maintaining generalizability. Specifically, we focus on the relation classification, where subject-object boxes are given and the model predicts the predicate between them. We tune on a held-in set and evaluate across multiple held-out datasets of varying complexity. Our approach strongly improves over its baselines and can infer unseen relation concepts, a capability absent in mainstream VRD methods. We demonstrate ART's practical value by using the predicted relations for segmenting complex scenes.

Recent advancements in large-scale generative models have significantly improved the quality and diversity of 3D shape generation. However, most existing methods focus primarily on generating static 3D models, overlooking the potential dynamic nature of certain shapes, such as humanoids, animals, and insects. To address this gap, we focus on rigging, a fundamental task in animation that establishes skeletal structures and skinning for 3D models. In this paper, we introduce OmniRig, the first large-scale rigging dataset, comprising 79,499 meshes with detailed skeleton and skinning information. Unlike traditional benchmarks that rely on predefined standard poses (e.g., A-pose, T-pose), our dataset embraces diverse shape categories, styles, and poses. Leveraging this rich dataset, we propose ARMO, a novel rigging framework that utilizes an autoregressive model to predict both joint positions and connectivity relationships in a unified manner. By treating the skeletal structure as a complete graph and discretizing it into tokens, we encode the joints using an auto-encoder to obtain a latent embedding and an autoregressive model to predict the tokens. A mesh-conditioned latent diffusion model is used to predict the latent embedding for conditional skeleton generation. Our method addresses the limitations of regression-based approaches, which often suffer from error accumulation and suboptimal connectivity estimation. Through extensive experiments on the OmniRig dataset, our approach achieves state-of-the-art performance in skeleton prediction, demonstrating improved generalization across diverse object categories. The code and dataset will be made public for academic use upon acceptance.

Face-to-face communication, as a common human activity, motivates the research on interactive head generation. A virtual agent can generate motion responses with both listening and speaking capabilities based on the audio or motion signals of the other user and itself. However, previous clip-wise generation paradigm or explicit listener/speaker generator-switching methods have limitations in future signal acquisition, contextual behavioral understanding, and switching smoothness, making it challenging to be real-time and realistic.In this paper, we propose an autoregressive (AR) based frame-wise framework called ARIG to realize the real-time generation with better interaction realism. To achieve real-time generation, we model motion prediction as a non-vector-quantized AR process. Unlike discrete codebook-index prediction, we represent motion distribution using diffusion procedure, achieving more accurate predictions in continuous space. To improve interaction realism, we emphasize interactive behavior understanding (IBU) and detailed conversational state understanding (CSU). In IBU, based on dual-track dual-modal signals, we summarize short-range behaviors through bidirectional-integrated learning and perform contextual understanding over long ranges. In CSU, we use voice activity signals and context features of IBU to understand the various states (interruption, feedback, pause, etc.) that exist in actual conversations. These serve as conditions for the final progressive motion prediction. Extensive experiments have verified the effectiveness of our model.

Video large language models have not yet been widely deployed, largely due to their tendency to hallucinate. Typical benchmarks for Video-LLMs rely simply on multiple choice questions. Unfortunately, VideoLLMs hallucinate far more aggressively on freeform text generation tasks like video captioning than they do on multiple choice verification tasks. To address this weakness, we propose ARGUS, a VideoLLM benchmark that measures freeform video captioning performance. By comparing VideoLLM outputs to human ground truth captions, ARGUS quantifies dual metrics. First, we measure the rate of hallucinations in the form of incorrect statements about video content or temporal relationships. Second, we measure the rate at which the model omits important descriptive details. Together, these metrics form a comprehensive view of video captioning.

Visual Robot Manipulation (VRM) aims to enable a robot to follow natural language instructions based on robot states and visual observations, and therefore requires costly multi- modal data. To compensate for the deficiency of robot data, existing approaches have employed vision-language pre- training with large-scale data. However, they either utilize web data that differs from robotic tasks, or train the model in an implicit way (e.g., predicting future frames at the pixel level), thus showing limited generalization ability under in- sufficient robot data. In this paper, we propose to learn from large-scale human action video datasets in an explicit way (i.e., imitating human actions from hand keypoints), introduc- ing Visual Robot Manipulation with Analogical Reasoning (AR-VRM). To acquire action knowledge explicitly from hu- man action videos, we propose a keypoint Vision-Language Model (VLM) pretraining scheme, enabling the VLM to learn human action knowledge and directly predict human hand keypoints. During fine-tuning on robot data, to facilitate the robotic arm in imitating the action patterns of human motions, we first retrieve human action videos that perform similar manipulation tasks and have similar historical obser- vations, and then learn the Analogical Reasoning (AR) map between human hand keypoints and robot components. Tak- ing advantage of focusing on action keypoints instead of irrel- evant visual cues, our method achieves leading performance on the CALVIN benchmark and real-world experiments. In few-shot scenarios, our AR-VRM outperforms previous meth- ods by large margins, underscoring the effectiveness of explicitly imitating human actions under data scarcity. Code available at https://github.com/idejie/ar.

Novel view synthesis (NVS) is a cornerstone for image-to-3d creation. However, existing works still struggle to maintain consistency between the generated views and the input views, especially when there is a significant camera pose difference, leading to poor-quality 3D geometries and textures. We attribute this issue to their treatment of all target views with equal priority according to our empirical observation that the target views closer to the input views exhibit higher fidelity. With this inspiration, we propose AR-1-to-3, a novel next-view prediction paradigm based on diffusion models that first generates views close to the input views, which are then utilized as contextual information to progressively synthesize farther views. To encode the generated view subsequences as local and global conditions for the next-view prediction, we accordingly develop a stacked local feature encoding strategy (Stacked-LE) and an LSTM-based global feature encoding strategy (LSTM-GE). Extensive experiments demonstrate that our method significantly improves the consistency between the generated views and the input views, producing high-fidelity 3D assets.

The challenge of multimodal semantic segmentation lies in establishing semantically consistent and segmentable multimodal fusion features under conditions of significant visual feature discrepancies. Existing methods commonly construct cross-modal self-attention fusion frameworks or introduce additional multimodal fusion loss functions to establish fusion features. However, these approaches often overlook the challenge caused by feature discrepancies between modalities during the fusion process. To achieve precise segmentation, we propose an Attention-Driven Multimodal Discrepancy Alignment Network (AMDANet). AMDANet reallocates weights to reduce the saliency of discrepant features and utilizes low-weight features as cues to mitigate discrepancies between modalities, thereby achieving multimodal feature alignment. Furthermore, to simplify the feature alignment process, a semantic consistency inference mechanism is introduced to reveal the network's inherent bias toward specific modalities, thereby compressing cross-modal feature discrepancies from the foundational level. Extensive experiments on the FMB, MFNet, and PST900 datasets demonstrate that AMDANet achieves mIoU improvements of 3.6%, 3.0%, and 1.6%, respectively, significantly outperforming state-of-the-art methods.

Accurately predicting the future trajectories of traffic agents is essential in autonomous driving. However, due to the inherent imbalance in trajectory distributions, tail data in natural datasets often represents more complex and hazardous scenarios. Existing studies typically rely solely on a base model's prediction error, without considering the diversity and uncertainty of long-tail trajectory patterns. We propose an adaptive momentum and decoupled contrastive learning framework (AMD), which integrates unsupervised and supervised contrastive learning strategies. By leveraging an improved momentum contrast learning (MoCo-DT) and decoupled contrastive learning (DCL) module, our framework enhances the model's ability to recognize rare and complex trajectories. Additionally, we design four types of trajectory random augmentation methods and introduce an online iterative clustering strategy, allowing the model to dynamically update pseudo-labels and better adapt to the distributional shifts in long-tail data. We propose three different criteria to define long-tail trajectories and conduct extensive comparative experiments on the nuScenes and ETH/UCY datasets. The results show that AMD not only achieves optimal performance in long-tail trajectory prediction but also demonstrates outstanding overall prediction accuracy.

Exemplar-based semantic image synthesis generates images aligned with semantic content while preserving the appearance of an exemplar. Conventional structure-guidance models like ControlNet, are limited as they rely solely on text prompts to control appearance and cannot utilize exemplar images as input. Recent tuning-free approaches address this by transferring local appearance via implicit cross-image matching in the augmented self-attention mechanism of pre-trained diffusion models. However, prior works are often restricted to single-object cases or foreground object appearance transfer, struggling with complex scenes involving multiple objects. To overcome this, we propose AM-Adapter (Appearance Matching Adapter) to address exemplar-based semantic image synthesis in-the-wild, enabling multi-object appearance transfer from a single scene-level image. AM-Adapter automatically transfers local appearances from the scene-level input. AM-Adapter alternatively provides controllability to map user-defined object details to specific locations in the synthesized images. Our learnable framework enhances cross-image matching within augmented self-attention by integrating semantic information from segmentation maps. To disentangle generation and matching, we adopt stage-wise training. We first train the structure-guidance and generation networks, followed by training the matching adapter while keeping the others frozen. During inference, we introduce an automated exemplar retrieval method for selecting exemplar image-segmentation pairs efficiently. Despite utilizing minimal learnable parameters, AM-Adapter achieves state-of-the-art performance, excelling in both semantic alignment and local appearance fidelity. Extensive ablations validate our design choices. Code and weights will be released.

3D semantic occupancy and flow prediction are fundamental to spatiotemporal scene understanding. This paper proposes a vision-based framework with three targeted improvements. First, we introduce an occlusion-aware adaptive lifting mechanism incorporating depth denoising. This enhances the robustness of 2D-to-3D feature transformation while mitigating reliance on depth priors. Second, we enforce 3D-2D semantic consistency via jointly optimized prototypes, using confidence- and category-aware sampling to address the long-tail classes problem. Third, to streamline joint prediction, we devise a BEV-centric cost volume to explicitly correlate semantic and flow features, supervised by a hybrid classification-regression scheme that handles diverse motion scales. Our purely convolutional architecture establishes new SOTA performance on multiple benchmarks for both semantic occupancy and joint occupancy semantic-flow prediction. We also present a family of models offering a spectrum of efficiency-performance trade-offs. Our real-time version exceeds all existing real-time methods in speed and accuracy, ensuring its practical viability.