视听学习

Estimating 3D attributes directly from images has advanced rapidly with the Visual Geometry Grounded Transformer (VGGT), which predicts camera parameters, depth maps, and point clouds in a single forward pass. However, its 1.2B-parameter scale severely limits deployment on resource-constrained platforms such as UAVs and mobile AR devices. To address this limitation, we introduce QVGGT, a tailored quantization framework designed to compress VGGT. Our approach starts from the observation that transformer blocks within VGGT exhibit heterogeneous sensitivity to quantization. We thus analyze per-block quantization sensitivity and propose a selective mixed-precision strategy that allocates higher precision to the most fragile transformer blocks. To address the amplification of quantization error caused by high-variance camera and register tokens, we further introduce token filtering with camera information compensation, which removes these outliers from activation calibration and restores their geometric cues using a PCA-derived global compensation token. Finally, we develop a task-aware scale search mechanism that evaluates candidate quantization scales not only through layer reconstruction but also through multi-head supervision and cross-head geometric consistency among camera poses, depth maps, and point maps.Extensive experiments on multiple geometry perception benchmarks demonstrate that QVGGT achieves near-lossless W4A16 quantization, preserving the accuracy of all 3D prediction heads while delivering 3 4.9xmemory reduction and up to 2.8x real hardware speedup over FP32.Our approach makes high-fidelity 3D perception feasible on edge devices, enabling practical deployment of feed-forward 3D reconstruction models in real-world constrained environments.

By 2026, up to 90% of online content may be synthetically generated, raising urgent concerns about the proliferation of AI-driven disinformation. In response, policymakers and technology companies are turning to watermarking as a safeguard: California's Bill AB 321 mandates watermarking of AI-generated media, while firms like Meta and Google have begun deploying watermarking systems to mitigate misuse. However, current watermarking methods remain brittle and vulnerable to attack. In this work, we introduce the visual paraphrase attack, a generative method that removes both visible and invisible watermarks from AI-generated images. The attack proceeds in two steps: (1) generating a descriptive caption from the original image, and (2) feeding this caption into a diffusion-based text-to-image model to produce a visually similar, watermark-free image. Our experiments show that this attack reliably removes watermarks while preserving semantic content of the original image, exposing a critical flaw in existing watermarking strategies. To counter this, we propose PECCAVI, the first watermarking technique explicitly designed to resist visual paraphrasing. PECCAVI embeds robust, high-fidelity watermarks (PSNR > 30 dB) in semantically stable image regions termed Non-Melting Points (NMPs) using multi-channel frequency domain encoding and noisy burnishing to obfuscate watermark locations and hinder reverse engineering. The method is model-agnostic and significantly more resilient than current alternatives. We also release the first benchmark dataset for visual paraphrasing attacks and open-source all code and resources, providing a foundation for future research on robust watermarking in the era of generative AI

General 3D foundation models have started to lead the trend of unifying diverse vision tasks, yet most assume RGB-only inputs and ignore readily available geometric cues (e.g., camera intrinsics, poses, and depth maps). To address this issue, we introduce OmniVGGT, a novel framework that can effectively benefit from an arbitrary number of auxiliary geometric modalities during both training and inference. In our framework, a GeoAdapter is proposed to encode depth and camera intrinsics/extrinsics into a spatial foundation model. It employs zero-initialized convolutions to progressively inject geometric information without disrupting the foundation model's representation space. This design ensures stable optimization with negligible overhead, maintaining inference speed comparable to VGGT even with multiple additional inputs. Additionally, a stochastic multimodal fusion regimen is proposed, which randomly samples modality subsets per instance during training. This enables an arbitrary number of modality inputs during testing and promotes learning robust spatial representations instead of overfitting to auxiliary cues. Extensive experiments on monocular/multi-view depth estimation, multi-view stereo, and camera pose estimation demonstrate that OmniVGGT outperforms prior methods with auxiliary inputs and achieves state-of-the-art results even with RGB-only input. To further highlight its practical utility, we integrated OmniVGGT into vision-language-action (VLA) models. The enhanced VLA model by OmniVGGT not only outperforms the vanilla point-cloud-based baseline on mainstream benchmarks, but also effectively leverages accessible auxiliary inputs to achieve consistent gains on robotic tasks. Project Page: https://livioni.github.io/OmniVGGT-official/

How do video understanding models acquire their answers? Although current Vision Language Models (VLMs) reason over complex scenes with diverse objects, action performances, and scene dynamics, understanding and controlling their internal processes remains an open challenge. Motivated by recent advancements in text-to-video (T2V) generative models, this paper introduces a logits-to-video (L2V) task alongside a model-independent approach, TRANSPORTER, to generate videos that capture the underlying rules behind VLMs' predictions. Given the high-visual-fidelity produced by T2V models, TRANSPORTER learns an optimal transport coupling to VLM's high-semantic embedding spaces. In turn, logit scores define embedding directions for conditional video generation. TRANSPORTER generates videos that reflect caption changes over diverse object attributes, action adverbs, and scene context. Quantitative and qualitative evaluations across VLMs demonstrate that L2V can provide a fidelity-rich, novel direction for model interpretability that has not been previously explored.

Recent advances in generative video modeling, driven by large-scale datasets and powerful architectures, have yielded remarkable visual realism. However, emerging evidence suggests that simply scaling data and model size does not endow these systems with an understanding of the underlying physical laws that govern real-world dynamics. Existing approaches often fail to capture or enforce such physical consistency, resulting in unrealistic motion and dynamics.In this work, we investigate whether integrating the inference of latent physical properties directly into the video generation process can equip models with the ability to produce physically plausible videos. To this end, we propose PHANTOM, a Physics-Infused Video Generation model that jointly models the visual content and latent physical dynamics. Conditioned on observed video frames and inferred physical states, PHANTOM jointly predicts latent physical dynamics and generates future video frames.PHANTOM leverages a physics-aware video representation that serves as an abstract yet informative embedding of the underlying physics, facilitating the joint prediction of physical dynamics alongside video content without requiring an explicit specification of a complex set of physical dynamics and properties. By integrating the inference of physical-aware video representation directly into the video generation process, PHANTOM produces video sequences that are both visually realistic and physically consistent.Quantitative and qualitative results on both standard video generation and physics-aware benchmarks demonstrate that PHANTOM not only outperforms existing methods in terms of adherence to physical dynamics but also delivers competitive perceptual fidelity.

We tackle the challenging task of generating complete 3D facial animations for two interacting, co-located participants from a mixed audio stream. While existing methods often produce disembodied "talking heads" akin to a video conference call, our work is the first to explicitly model the dynamic 3D spatial relationship--including relative position, orientation, and mutual gaze--that is crucial for realistic in-person dialogues. Our system synthesizes the full performance of both individuals, including precise lip-sync, and uniquely allows their relative head poses to be controlled via textual descriptions. To achieve this, we propose a dual-stream architecture where each stream is responsible for one participant's output. We employ speaker's role embeddings and inter-speaker cross-attention mechanisms are designed to disentangle the mixed audio and model the interaction. Furthermore, we introduce a novel eye gaze loss to promote natural, mutual eye contact. To power our data-hungry approach, we introduce a novel pipeline to curate a large-scale conversational dataset consisting of over 2 million dyadic pairs from in-the-wild videos. Our method generates fluid, controllable, and spatially aware dyadic animations suitable for immersive applications in VR and telepresence, significantly outperforming existing baselines in perceived realism and interaction coherence.

Accurate 3D scene understanding is essential for embodied intelligence, with occupancy prediction emerging as a key task for reasoning about both objects and free space. Existing approaches largely rely on depth priors (e.g., DepthAnything) but make only limited use of 3D cues, restricting performance and generalization. Recently, visual geometry models such as VGGT have shown strong capability in providing rich 3D priors, but similar to monocular depth foundation models, they still operate at the level of visible surfaces rather than volumetric interiors, motivating us to explore how to more effectively leverage these increasingly powerful geometry priors for 3D occupancy prediction. We present GPOcc, a framework that leverages generalizable visual geometry priors (GPs) for monocular occupancy prediction. Our method extends surface points inward along camera rays to generate volumetric samples, which are represented as Gaussian primitives for probabilistic occupancy inference. To handle streaming input, we further design a training-free incremental update strategy that fuses per-frame Gaussians into a unified global representation. Experiments on Occ-ScanNet and EmbodiedOcc-ScanNet demonstrate significant gains: GPOcc improves mIoU by +9.99 in the monocular setting and +11.79 in the streaming setting over prior state of the art. Under the same depth prior, it achieves +6.73 mIoU while running 2.65 times faster. These results highlight that GPOcc leverages geometry priors more effectively and efficiently. Code will be released at https://github.com/JuIvyy/GPOcc.

We propose JUMP-Hand, a novel multi-view 3D hand reconstruction method that explicitly models probabilistic joint-wise uncertainty as a gating mechanism for multi-view fusion. Existing approaches usually rely on naive pooling or implicit attention, overlooking that each hand joint exhibits varying visibility and reliability across views. Such indiscriminate aggregation of noisy or unreliable information inevitably degrades overall performance. For instance, a joint severely occluded in one view might be clearly visible in another. To address this, JUMP-Hand draws inspiration from the Mixture of Experts (MoE) paradigm, treating each 2D view as a specialized expert. The key idea is that the reliability of each view expert is quantified through joint-wise uncertainty modeling, serving as an explicit gating signal to route experts' partial yet complementary clues for each joint in a coarse-to-fine reconstruction paradigm. In this design, uncertainty not only guides the uncertainty-aware triangulation for reliable 3D hand initialization during the coarse stage, but also acts as a gating signal during the refinement stage to adaptively aggregate multi-scale features from different view experts on a joint-wise basis, enabling robust 3D hand reconstruction. Extensive experiments on DexYCB-MV, HO3D-MV, and OakInk-MV demonstrate that our method consistently achieves state-of-the-art results, validating the effectiveness of the proposed method with joint-wise uncertainty gating for reliable 3D hand reconstruction. Code is available at https://github.com/HaohongKuang/JUMP-Hand.

Despite the significant advancements in Large Vision-Language Models (LVLMs), their tendency to generate hallucinations undermines reliability and restricts broader practical deployment. Among the hallucination mitigation methods, feature steering emerges as a promising approach that reduces erroneous outputs in LVLMs without increasing inference costs. However, current methods apply uniform feature steering across all layers. This heuristic strategy ignores inter-layer differences, potentially disrupting layers unrelated to hallucinations and ultimately leading to performance degradation on general tasks. In this paper, we propose Locate-Then-Sparsify for Feature Steering (LTS-FS), a plug-and-play framework which controls the steering intensity according to the hallucination relevance of each layer. We first construct a dataset comprising token-level and sentence-level hallucination cases. Based on this dataset, we introduce an attribution method based on causal interventions to quantify the hallucination relevance of each layer. With the attribution scores across layers, we propose a layerwise strategy that converts these scores into feature steering intensities for individual layers, enabling more precise adjustments specifically on hallucination-relevant layers. Extensive experiments across multiple LVLMs and benchmarks demonstrate that LTS-FS effectively mitigates hallucination while preserving strong performance. Codes are available at https://github.com/huttersadan/LTS-FS.

Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods for generating such captions often rely on distilling the captions from pretrained LMMs, constructing them from publicly available internet images, or even generating them through human annotation. However, these strategies can fall short in terms of precision and granularity, particularly when dealing with complex visual reasoning tasks. In this paper, we propose to leverage off-the-shelf visual specialists, which were trained from annotated images initially not for image captioning, for enhancing the image caption. Our approach, named Cap-Workflow, explores object low-level and fine-grained attributes (e.g., depth, emotion and fine-grained categories) and object relations (e.g., relative location and human-object-interaction (HOI)), and combine the attributes into the descriptive caption. By systematically integrating these rich attributes into the generated captions, Cap-Workflow significantly improves the descriptive quality of the captions, providing a deeper and more nuanced understanding of the visual content. Experiments demonstrate that such visual specialists are able to improve the performance for visual understanding tasks as well as reasoning that benefits from more accurate visual understanding. The source code and datasets are available at https://github.com/syp2ysy/Cap-Workflow.

Visual localization is a core technology for augmented reality and autonomous navigation. Recent methods combine the efficient rendering of 3D Gaussian Splatting (3DGS) with feature-based localization. These methods rely on direct matching between 2D query features and the 3D Gaussian feature field, but this often results in mismatches due to an inherent bias in the learned Gaussian feature. We theoretically analyze the feature learning process in 3DGS, revealing that the widely adopted alpha-blending optimization inherently introduces bias into 3D point features. This bias stems from the entanglement between individual Gaussians and their neighboring Gaussians, making the learned features unsuitable for precise matching tasks. Motivated by these findings, we propose ULF-Loc, an unbiased landmark feature framework that replaces biased feature optimization with geometry-weighted feature fusion. We further introduce keypoint-consensus landmark sampling to select reliable Gaussians and local geometric consistency verification to reject mismatches caused by rendering artifacts. On the Cambridge Landmarks dataset, ULF-Loc reduces the mean median translation error by 17% compared to the state-of-the-art, while achieving superior efficiency with only 1/10 the training time and 1/6 the GPU memory of STDLoc. Our code is accessible at https://github.com/Cyril-gyd/ULF-Loc.

Reliable 3D reconstruction from in-the-wild image collections is often hindered by noisy images--irrelevant inputs with little or no view overlap with others. While traditional Structure-from-Motion pipelines handle such cases through geometric verification and outlier rejection, feed-forward 3D reconstruction models lack these explicit mechanisms, leading to degraded performance under in-the-wild conditions. In this paper, we discover that the existing feed-forward reconstruction model, e.g., VGGT, despite lacking explicit outlier-rejection mechanisms or noise-aware training, can inherently distinguish distractor images. Through an in-depth analysis under varying proportions of synthetic distractors, we identify a specific layer that naturally exhibits outlier-suppressing behavior. Further probing reveals that this layer encodes discriminative internal representations that enable an effective noise-filtering capability, which we simply leverage to perform outlier-view rejection in feed-forward 3D reconstruction without any additional fine-tuning or supervision. Extensive experiments on both controlled and in-the-wild datasets demonstrate that this implicit filtering mechanism is consistent and generalizes well across diverse scenarios.

Cinematic Audio Source Separation (CASS) aims to decompose mixed film audio into speech, music, and sound effects, enabling applications like dubbing and remastering. Existing CASS approaches are audio-only, overlooking the inherent audio-visual nature of films, where sounds often align with visual cues. We present the first framework for audio-visual CASS (AV-CASS), leveraging visual context to enhance separation quality. Our method formulates CASS as a conditional generative modeling problem using conditional flow matching, enabling multimodal audio source separation. To address the lack of cinematic datasets with isolated sound tracks, we introduce a training data synthesis pipeline that pairs in-the-wild audio and video streams (e.g., facial videos for speech, scene videos for effects) and design a dedicated visual encoder for this dual-stream setup. Trained entirely on synthetic data, our model generalizes effectively to real-world cinematic content and achieves strong performance on synthetic, real-world, and audio-only CASS benchmarks. Code and demo are available at https://cass-flowmatching.github.io.

Existing 3D point tracking methods mostly rely on heuristic designs or scene reconstruction, which incurs significant computational overhead and makes it difficult to meet the demands of real-time applications. To address this problem, in this work, we present a novel spatial tracker that leverages a feed-forward visual geometry transformer to predict the trajectories of arbitrary query points from monocular videos in real time. Specifically, we employ a query initialization mechanism to maintain and update a global feature vector and a set of frame-level feature vectors for each query point. Then, we propose a new spatial tracking framework, which consists of a visual geometry transformer backbone, a global embedding branch, a frame-level embedding branch, and a tracking head. The key innovation lies in the dual-branch embedding design, where the global embedding branch integrates geometry-grounded features of the entire video into global query features to optimize track information across the entire sequence and the frame-level branch combines geometry-grounded features of each respective frame into frame-level query features to refine fine-grained track coordinate predictions. Furthermore, to facilitate collaboration between the global branch and the frame-level branch, we introduce an interaction module which enables unidirectional or bidirectional information exchange between the global query features and frame-level query features. Extensive experiments on various point tracking benchmark datasets show that our approach achieves significantly fast spatial tracking speed compared with state-of-the-art methods, while maintaining comparable tracking accuracy.

Medical visual question answering models often face potential train-test distribution shifts that hinder generalization across unseen imaging and linguistic patterns. To address this challenge, we propose a dual-level confidence based framework (DuCoR) that achieves implicit self-refinement through iterative pseudo-supervised optimization. Instead of relying on fixed pseudo answers, the model progressively refines its predictions by estimating their reliability from two complementary perspectives. A loss-level confidence captures the reliability of supervision by modeling clean and noisy loss distributions, while a feature-level confidence measures the semantic coherence between sample representations and their pseudo-answer conditioned prototypes. Since these two confidences originate from distinct information sources, including the supervision signal and the input semantics, they provide mutually corrective cues. They are adaptively fused to derive per-sample reliability weights that guide pseudo-supervised optimization toward better alignment with the target distribution. Extensive experiments on multiple medical VQA benchmarks show that our method achieves superior performance and exhibits improved cross-domain generalization over fully supervised baseline.

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in high-resolution or multi-image scenarios. To address this issue, we propose EvoComp, a visual token compression framework that significantly reduces token count while preserving task accuracy. EvoComp introduces a lightweight encoder-only transformer-based compressor that selects the most informative and non-redundant visual tokens by jointly considering visual and textual contexts. A core challenge lies in providing effective supervision for training the compressor. To this end, we design an evolutionary labeling strategy that searches for token subsets minimizing the MLLM's output loss, while enforcing semantic diversity through vocabulary-based token grouping. We further train the compressor using a tailored loss function combining the GHM loss to mitigate class and difficulty imbalance, and a cosine similarity regularization to encourage semantic separation between retained and discarded tokens. Extensive experiments across multiple vision-language benchmarks show that EvoComp outperforms existing methods based on attention or similarity heuristics. Notably, it retains 99.3% of the original accuracy under 3x token compression and delivers up to 1.6x speedup on mobile devices.

Diffusion models have shown impressive performance in generative tasks, demonstrating their ability to capture detailed structural and semantic information. Recently, these capabilities have been extended to visual understanding, with studies employing diffusion models as the backbone for various perception tasks. However, existing diffusion-based perception models are generally restricted to a single task or a fixed set of predefined tasks, lacking an efficient mechanism to generalize to novel tasks. To overcome this limitation, we propose a unified DiT-based perception framework called UniPercept, which introduces a novel foundation-adapter paradigm for general visual perception. In this framework, a shared diffusion-based foundation model is trained to capture common and generalizable visual knowledge across diverse perception tasks, with task-specific adapters integrated for each individual task. Leveraging its superior generalization ability, the foundation model can be efficiently adapted to novel domains through lightweight adapters, requiring as few as **1,000** training samples and less than **1%** of trainable parameters. Furthermore, UniPercept demonstrates strong performance across various perception tasks, outperforming state-of-the-art generalist models in most cases and achieving accuracy comparable to specialist models. Project page: https://VIPL-GENUN.github.io/Project-UniPercept.

3D visual grounding task aims to accurately identify and grounding target objects in 3D space based on natural language descriptions,where the effective exploitation of relative relations between the target and anchor is crucial.However, in existing methods, relative relations are often tightly entangled with entity semantics. This tight coupling encourages models to rely on semantic shortcuts from entity names, making it difficult to maintain good generalization under multi-view and complex multi-object scenarios.To address this, we propose an object-relation decoupling framework that treats target-anchor relations as first-class geometric and semantic primitives and models them explicitly.First, we construct a scene-level relative geometric representation that encodes the direction and distance between the target and anchor, and introduce a scene-level hyper-object token as a unified prior for scale and viewpoint.Second, we develop a predicate-decoupled cross-modal alignment strategy that preserves only predicates carrying spatial relational semantics while masking out all other tokens, thereby suppressing semantic leakage from entity names.Finally, we design an anchor-guided regression module that predicts auxiliary anchors and samples their features to guide the model in learning entity semantics from text, explicitly injecting target-anchor priors and effectively resolving ambiguities in complex multi-object scenes.Extensive experiments on multiple 3D visual grounding benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches and exhibits strong robustness and generalization under challenging multi-view and relation-intensive settings.

Natural videos exhibit heterogeneous temporal dynamics, with certain segments undergoing high-dynamic scene transitions and others dominated by low-dynamic visual changes. However, treating all frames identically, a common practice in most MLLMs, leads to redundant visual encoding, which results in significant computational overhead. The recent state-of-the-art model, i.e., Qwen2.5-VL, adopts a fixed two-frame encoding scheme, but our pilot experiments indicate that it encounters a visual confusion problem under high-dynamic frame pairs. To address this issue, we propose FlexiVideo, an efficient MLLM that models temporal dynamics leveraging visual variation. FlexiVideo first employs an adaptive temporal segmentation module to estimate inter-frame differences, grouping consecutive frames into scene segments with subtle visual changes. Subsequently, a dynamical spatio-temporal embedding module adjusts the temporal window for scene-level encoding. By restructuring scene-level visual representations within a structured temporal organization, our approach models dynamics more effectively and reduces the encoding burden while preserving fine-grained visual variations. Extensive experiments show that FlexiVideo-3B consistently outperforms Qwen2.5-VL-3B across 6 general video benchmarks. Notably, when evaluated on MotionBench at 10 FPS, FlexiVideo-3B reduces visual tokens by 43.5% compared with Qwen2.5-VL-3B while achieving a 1.3% performance gain, striking a significantly better balance between efficiency and effectiveness. Code and checkpoints are available at github.com/AI9Stars/FlexiVideo.

Recent advances in language and vision have demonstrated that scaling up model capacity consistently improves performance across diverse tasks.In 3D visual geometry reconstruction, large-scale training has likewise proven effective for learning versatile representations.However, further scaling of 3D models is challenging due to the complexity of geometric supervision and the diversity of 3D data. To overcome these limitations, we propose MoRE, a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture that dynamically routes features to task-specific experts, allowing them to specialize in complementary data aspects and enhance both scalability and adaptability.Aiming to improve robustness under real-world conditions, MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation.In addition, it integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction.MoRE is further optimized with tailored loss functions to ensure robust learning across diverse inputs and multiple geometric tasks.Extensive experiments demonstrate that MoRE achieves state-of-the-art performance across multiple benchmarks and supports effective downstream applications without extra computation.