Controllable video character replacement with a user-provided identity remains a challenging problem due to the lack of paired video data. Prior works have predominantly relied on a reconstruction-based paradigm that requires per-frame segmentation masks and explicit structural guidance (e.g., skeleton, depth). This reliance, however, severely limits their generalizability in complex scenarios involving occlusions, character-object interactions, unusual poses, or challenging illumination, often leading to visual artifacts and temporal inconsistencies. In this paper, we propose MoCha, a new framework that mitigates these limitations by harnessing the inherent tracking ability of the video diffusion model, therefore requiring only a single arbitrary frame mask and no structural guidance. To effectively adapt the multi-modal input condition and enhance facial identity, we introduce a condition-aware RoPE and employ an RL-based post-training stage. Furthermore, to overcome the scarcity of qualified paired-training data, we propose a comprehensive data construction pipeline. Specifically, we design three specialized datasets: a high-fidelity rendered dataset built with Unreal Engine 5 (UE5), an expression-driven dataset synthesized by current portrait animation techniques, and an augmented dataset derived from existing video-mask pairs. Extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches. We will release the code and dataset to facilitate further research.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Digital characters are central to modern media, yet generating character videos with long-duration, consistent multi-view appearance and expressive identity remains challenging. Existing approaches either provide insufficient context to preserve identity or leverage non-character-centric information as the "memory", leading to suboptimal consistency.Recognizing that character video generation inherently resembles an "outside-looking-in" scenario. In this work, we propose represent the character's visual attributes through a compact set of anchor frames.This design provides stable references for consistency, while reference-based video generation inherently faces challenges of copy-pasting and multi-reference conflicts. To address these, we introduce two mechanisms: Superset Content Anchoring, providing intra- and extra-training clip cues to prevent duplication, and RoPE as Weak Condition, encoding positional offsets to distinguish multiple anchors.Furthermore, we construct a scalable pipeline to extract these anchors from massive videos. Experiments show our method generates high-quality character videos exceeding 10 minutes, and achieves expressive identity and appearance consistency across views, surpassing existing methods.
Open-domain visual entity recognition (VER) seeks to associate images with entities in encyclopedic knowledge bases such as Wikipedia. Recent generative methods tailored for VER demonstrate strong performance but incur high computational costs, limiting their scalability and practical deployment. In this work, we revisit the contrastive paradigm for VER and introduce WikiCLIP, a simple yet effective framework that establishes a strong and efficient baseline for open-domain VER. WikiCLIP leverages large language model embeddings as knowledge-rich entity representations and enhances them with a Vision-Guided Knowledge Adaptor (VGKA) that aligns textual semantics with visual cues at the patch level. To further encourage fine-grained discrimination, a Hard Negative Synthesis Mechanism generates visually similar but semantically distinct negatives during training. Experimental results on popular open-domain VER benchmarks, such as OVEN, demonstrate that WikiCLIP significantly outperforms strong baselines. Specifically, WikiCLIP achieves a 16% improvement on the challenging OVEN unseen set, while reducing inference latency by nearly 100 times compared with the leading generative model, AutoVER. The project page is available at https://artanic30.github.io/project_pages/WikiCLIP/.
Despite rapid developments and widespread applications of MLLM agents, they still struggle with long-form video understanding (LVU) tasks, which are characterized by high information density and extended temporal spans. Recent research on LVU agents demonstrates that simple task decomposition and collaboration mechanisms are insufficient for long-chain reasoning tasks. Moreover, directly reducing the time context through embedding-based retrieval may lose key information of complex problems. In this paper, we propose Symphony, a multi-agent system, to alleviate these limitations. By emulating human cognition patterns, Symphony decomposes LVU into fine-grained subtasks and incorporates a deep reasoning collaboration mechanism enhanced by reflection, effectively improving the reasoning capability. Additionally, Symphony provides a VLM-based grounding approach to analyze LVU tasks and assess the relevance of video segments, which significantly enhances the ability to locate complex problems with implicit intentions and large temporal spans. Experimental results show that Symphony achieves state-of-the-art performance on LVBench, LongVideoBench, VideoMME, and MLVU, with a 5.0% improvement over the prior state-of-the-art method on LVBench. Code is available at https://github.com/Haiyang0226/Symphony.
Recent advances in 3D Gaussian Splatting (3DGS) enable photorealistic real-time rendering but also increase the risks of unauthorized copying and redistribution. Existing 3DGS watermarking methods typically rely on handcrafted thresholds or globally fixed hyperparameters to balance invisibility and robustness, making their embedding behavior static and scene-agnostic. We instead formulate 3DGS watermarking as a goal-directed decision process and introduce Write Where It Matters (W2M), the first reinforcement learning-based framework that adaptively learns where and how much to embed. By modeling the embedding process as a Markov Decision Process, W2M uses a lightweight policy network to allocate precise Gaussian updates directly from immediate reward feedback, iteratively. The reward incentivizes both rendering-space invisibility and decoding robustness under various image- and model-level distortions. To achieve efficiency, W2M operates on a structured 3DGS backbone organized around learnable anchors and applies policy-guided per-anchor gradient scaling. Extensive experiments across the Blender, LLFF, and Mip-NeRF 360 datasets demonstrate that W2M achieves state-of-the-art bit accuracy, strong perceptual fidelity, and structural consistency under both standard and adversarial conditions.
Given an image and a descriptive prompt, image inversion seeks to identify the initial noise that, when denoised, accurately reconstructs the original image. This is crucial for applications like image editing, which can be achieved by denoising the inverted noise with an edited prompt. Existing methods often rely on approximations. They often require many steps, leading to inaccuracies, slow processing, and artifacts due to the inherent intractability in the inversion process. To overcome these issues, in this work, we propose FlashIn, a novel algorithm for faster and more accurate image inversion, enabling high-quality, real-time editing. FlashIn offers two main contributions: i) A learnable neural network directly maps an image to its corresponding noise. Trained with a cycle-consistent strategy using generated data and seed noise, this approach yields a more efficient and precise inversion model. ii) Adversarial training aligns noise-reconstructed images with real ones, enhancing inversion accuracy and editing quality. These strategies enable a fast, accurate inversion process in a single step, with further improvements possible through additional steps. Integrated with few-step diffusion models such as Flux.1-Schnell, our method achieves high-quality image editing within one second on a single GPU, facilitating real-time, interactive editing. Extensive experiments demonstrate that FlashIn delivers state-of-the-art inversion precision and impressive editing results across various scenarios and applications.
Predicting driver attention is a critical problem for developing explainable autonomous driving systems and understanding driver behavior in mixed human-autonomous vehicle traffic scenarios. Although significant progress has been made through large-scale driver attention datasets and deep learning architectures, existing works are constrained by narrow frontal field-of-view and limited driving diversity. Consequently, they fail to capture the full spatial context of driving environments, especially during lane changes, turns, and interactions involving peripheral objects such as pedestrians or cyclists. In this paper, we introduce DriverGaze360, a large-scale 360 field of view driver attention dataset, containing 1 million gaze-labeled frames collected from 19 human drivers, enabling comprehensive omnidirectional modeling of driver gaze behavior. Moreover, our panoramic attention prediction approach, DriverGaze360-Net, jointly learns attention maps and attended objects by employing an auxiliary semantic segmentation head. This improves spatial awareness and attention prediction across wide panoramic inputs. Extensive experiments demonstrate that DriverGaze360-Net achieves state-of-the-art attention prediction performance on multiple metrics on panoramic driving images. Dataset and method available at https://dfki-av.github.io/drivergaze360/.
DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding
PDF ↗Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems from two fundamental challenges: 1) a low Signal-to-Noise Ratio (SNR), with crucial evidence buried in irrelevant pages; and 2) supervision scarcity, as datasets offering only final short answers provide a weak learning signal. In this paper, we address these challenges by proposing a paradigm that requires the model to execute a structured "Analysis, Localization and Reasoning" workflow. To instill this capability, we design a two-stage training framework: we first perform Supervised Fine-Tuning on high-quality data generated via an efficient knowledge distillation strategy. Subsequently, we employ an Evidence-aware Group Relative Policy Optimization which jointly optimizes for both evidence localization and answer accuracy. Additionally, we introduce a Evidence-Guided Resolution Allocation strategy to mitigate memory constraints of training on multi-pages documents. Extensive experiments demonstrate that DocSeeker achieves superior performance on both in-domain and out-of-domain tasks. We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems, serving as an ideal foundation for their implementation.
Internet photo collections exhibit an extremely long-tailed distribution: a few famous landmarks are densely photographed and easily reconstructed in 3D, while most real-world sites are represented with sparse, noisy, uneven imagery beyond the capabilities of both classical and learned 3D methods. We believe that tackling this long-tail regime represents one of the next frontiers for 3D foundation models. Although reliable ground-truth 3D supervision from sparse scenes is challenging to acquire, we observe that it can be effectively simulated by sampling sparse subsets from well-reconstructed Internet landmarks. To this end, we introduce MegaDepth-X, a large dataset of 3D reconstructions with clean, dense depth, together with a strategy for sampling sets of training images that mimic camera distributions in long-tail scenes. Finetuning 3D foundation models with these components yields robust reconstructions under extreme sparsity, and also enables more reliable reconstruction in symmetric and repetitive scenes, while preserving generalization to standard, dense 3D benchmark datasets.
Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grounding. Nevertheless, recent work shows that while VLMs often manage to capture the correct image region corresponding to the question, they do not necessarily produce the correct answers. In this work, we demonstrate that this misalignment could be attributed to suboptimal information flow within VLMs, where text tokens distribute too much attention to irrelevant visual tokens, leading to incorrect answers. Based on the observation, we show that modulating the information flow during inference can improve the perception capability of VLMs. The idea is that text tokens should only be associated with important visual tokens during decoding, eliminating the interference of irrelevant regions. To achieve this, we propose a token dynamics-based method to determine the importance of visual tokens, where visual tokens that exhibit distinct activation patterns during different decoding stages are viewed as important. We apply our approach to representative open-source VLMs and evaluate on various datasets, including visual question answering, visual grounding and counting, optical character recognition, and object hallucination. The results show that our approach significantly improves the performance of baselines. Project page: https://cxliu0.github.io/AIF/.
Recent advances in Vision-Language Models (VLMs) have enabled video-instructed robotic programming, allowing agents to interpret video demonstrations and generate executable control code. We formulate video-instructed robotic programming as a cross-domain adaptation problem, where perceptual and physical differences between demonstration and deployment induce procedural mismatches. However, current VLMs lack the procedural understanding needed to reformulate causal dependencies and achieve task-compatible behavior under such domain shifts. We introduce NeSyCR, a neurosymbolic counterfactual reasoning framework that enables verifiable adaptation of task procedures, providing a reliable synthesis of code policies. NeSyCR abstracts video demonstrations into symbolic trajectories that capture the underlying task procedure. Given deployment observations, it derives counterfactual states that reveal cross-domain incompatibilities. By exploring the symbolic state space with verifiable checks, NeSyCR proposes procedural revisions that restore compatibility with the demonstrated procedure. NeSyCR achieves a 31.14% improvement in task success over the strongest baseline Statler, showing robust cross-domain adaptation across both simulated and real-world manipulation tasks.
Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning. In this paper, we propose a framework to equip MLLMs with multi-frame spatial understanding by integrating fundamental spatial skills, including depth perception, visual correspondence, and dynamic perception. We design a novel data pipeline and collect the MultiSPA dataset of more than 27 million samples spanning diverse 3D and 4D scenes to enable training. Alongside MultiSPA, we introduce a comprehensive benchmark that tests a wide spectrum of spatial tasks under uniform metrics. Our resulting model, Multi-SpatialMLLM, achieves significant gains over baselines and proprietary systems, demonstrating scalable and generalizable multi-frame perception. We further observe multi-task benefits and emergent spatial capabilities in challenging scenarios, and showcase how our model can serve as a multi-frame reward annotator for robotics.
Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining
PDF ↗Test-time prompt tuning (TPT) has emerged as a promising technique for enhancing the adaptability of vision-language models by optimizing textual prompts using unlabeled test data. However, prior studies have observed that TPT often produces poorly calibrated models, raising concerns about the reliability of their predictions. Recent works address this issue by incorporating additional regularization terms that constrain model outputs, which improve calibration but often degrade performance. In this work, we reveal that these regularization strategies implicitly encourage optimization toward flatter minima, and that the sharpness of the loss landscape around adapted prompts is a key factor governing calibration quality. Motivated by this observation, we introduce Flatness-aware Prompt Pretraining (FPP), a simple yet effective pretraining framework for TPT that initializes prompts within flatter regions of the loss landscape prior to adaptation. We show that simply replacing the initialization in existing TPT pipelines--without modifying any other components--is sufficient to improve both calibration and performance. Notably, FPP requires no labeled data and incurs no additional computational costs during test-time tuning, making it highly practical for real-world deployment. The code is available at: https://github.com/YonseiML/fpp.
Document Visual Question Answering (DocVQA) remains challenging for existing Vision-Language Models (VLMs), especially under complex reasoning and multi-step workflows. Current approaches struggle to decompose intricate questions into manageable sub-tasks and often fail to leverage specialized processing paths for different document elements. We present ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering, a novel multi-agent framework that addresses these limitations through strategic agent coordination and iterative refinement. ORCA begins with a reasoning agent that decomposes queries into logical steps, followed by a routing mechanism that activates task-specific agents from a specialized agent dock. Our framework leverages a set of specialized AI agents, each dedicated to a distinct modality, enabling fine-grained understanding and collaborative reasoning across diverse document components. To ensure answer reliability, ORCA employs a debate mechanism with stress-testing, and when necessary, a thesis-antithesis adjudication process. This is followed by a sanity checker to ensure format consistency. Extensive experiments on three benchmarks demonstrate that our approach achieves significant improvements over state-of-the-art methods, establishing a new paradigm for collaborative agent systems in vision-language reasoning.
Pose estimation remains challenging under sparse views, especially when visual overlap across images is extremely limited. Recent advances in video generation models offer a promising solution by enabling keyframe interpolation, which can enrich contextual cues and improve pose estimation performance. However, existing video generation models often lack 3D consistency, producing temporally plausible but spatially inconsistent frames that degrade downstream pose estimation. In this paper, we propose a framework ExPose that directly addresses 3D inconsistency when applying video generation to pose estimation in extreme-view settings. Specifically, we fine-tune a video generation model using Group Relative Preference Optimization (GRPO), aligning its outputs with 3D-consistent supervisory signals derived from pose estimation objectives. Our approach not only enhances the quality of temporal interpolation, but also ensures spatial coherence across views, significantly improving pose estimation accuracy. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines, highlighting the potential of preference-optimized video generation as a powerful tool for pose estimation in extreme-view scenarios. Code is available at https://github.com/yh-yoon/ExPose.
Recent advancements in generative video codec (GVC) typically encode video into a 2D latent grid and employ high-capacity generative decoders for reconstruction. However, this paradigm still leaves two key challenges in fully exploiting spatial-temporal redundancy: Spatially, the 2D latent grid inevitably preserves intra-frame redundancy due to its rigid structure, where adjacent patches remain highly similar, thereby necessitating a higher bitrate. Temporally, the 2D latent grid is less effective for modeling long-term correlations in a compact and semantically coherent manner, as it hinders the aggregation of common contents across frames. To address these limitations, we introduce Generative Video Compression with One-Dimensional (1D) Latent Representation (GVC1D). GVC1D encodes the video data into extreme compact 1D latent tokens conditioned on both short- and long-term contexts. Without the rigid 2D spatial correspondence, these 1D latent tokens can adaptively attend to semantic regions and naturally facilitate token reduction, thereby reducing spatial redundancy. Furthermore, the proposed 1D memory provides semantically rich long-term context while maintaining low computational cost, thereby further reducing temporal redundancy. Experimental results indicate that GVC1D attains superior compression efficiency, where it achieves bitrate reductions of 60.4% under LPIPS and 68.8% under DISTS on the HEVC Class B dataset, surpassing the previous video compression methods.
COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation
PDF ↗Estimating the 6DoF pose of a novel object with a single reference view is challenging due to occlusions, view-point changes, and outliers. A core difficulty lies in finding robust cross-view correspondences, as existing methods often rely on discrete one-to-one matching that is non-differentiable and tends to collapse onto sparse keypoints. We propose Confidence-aware Optimal Geometric Correspondence (COG), an unsupervised framework that formulates correspondence estimation as a confidence-aware optimal transport problem. COG produces balanced soft correspondences by predicting point-wise confidences and injecting them as optimal transport marginals, suppressing non-overlapping regions. Semantic priors from vision foundation models further regularize the correspondences, leading to stable pose estimation. This design integrates confidence into the correspondence finding and pose estimation pipeline, enabling unsupervised learning. Experiments show unsupervised COG achieves comparable performance to supervised methods, and supervised COG outperforms them. Codes: https://github.com/YC-Che/COG
Recent works on vision-language-action (VLA) models have made great progress in exploring action tokenizers that convert continuous control signals into discrete tokens to align with LLM/VLM training paradigms.These approaches typically train a single tokenizer over entire manipulation trajectories, which often comprise multiple distinct skills and thus pose a challenging optimization trade-off.To address this issue, we introduce MoEActok, a novel action tokenizer that employs a mixture-of-experts (MoE) quantizer to produce skill-aware discrete representations for VLA models. MoEActok utilizes a clustering-driven MoE VQ-VAE mechanism in which each expert specializes in a particular skill.The key components are: (a) an action-skill decoupling strategy that uses k-means clustering to group action chunks, aligning clusters having similar skills; (b) a skill-aware training paradigm that augments VLA models with skill-conditioned context, improving skill grounding; and (c) an adapter that projects shared encoder representations into skill-specific latent spaces for specialized quantization, and subsequently harmonize the heterogeneous quantized representations back into a unified space for coherent reconstruction by the shared decoder.We evaluate MoEActok-based VLA models against multiple prior action tokenizer baselines in the RoboTwin and Simpler-Env simulators, and further assess zero-shot transfer on three real-world tasks. Across both simulated and real-world settings, MoEActok-based VLA substantially outperforms existing discrete tokenization methods.
Metric depth estimation aims to recover depth maps with absolute scale, high resolution, and cross-scene consistency from visual observations. Existing approaches either rely on large-scale models or costly sensors to preserve metric accuracy and generalization, both ill-suited to resource-constrained deployment. In this paper, we propose LiteSense, a lightweight RGB-ToF fusion framework that leverages compact normalized histogram (CNH) signals together with RGB cues to achieve efficient and reliable metric depth estimation. Specifically, LiteSense leverages a U-Net-style encoder-decoder that forms an RGB-D input by concatenating RGB with upsampled ToF depth, providing explicit metric priors. To address resolution disparity and recover fine details, we introduce the **Patch-wise CNH Spatial Injection (PCSI)** module, which leverages zone-wise histogram measurements via cross-attention to guide high-level feature fusion. Extensively evaluated on NYUv2 and SUN RGB-D, LiteSense consistently outperforms monocular baselines and DELTAR with substantially lower computational cost, and demonstrates promising zero-shot generalization. We further introduce THDR3K, the first indoor RGB-ToF-CNH dataset, where LiteSense achieves real-world accuracy comparable to--and in challenging cases surpassing--Intel RealSense. All the relevant source codes and the collected dataset are available at GitHub.
Dataset Distillation (DD) seeks to create small, synthetic datasets for efficient model training. While diffusion models are powerful generators, their use in DD is hampered by distribution shifts between synthetic and ideal distilled data, leading to suboptimal performance. We identify two critical shifts. First, considering the small capacity of the synthetic data, an optimal synthetic distribution for DD should be a simplification of the real data distribution, rather than replicating the original data's complexity. Second, there is a hazardous empirical deviation in the synthetic dataset from this learned distribution due to the data sampling process. To address these, we introduce a two-stage approach. During diffusion training time, we mitigate the distribution shift by employing an L1 sparsity regularizer, compelling the diffusion model to learn a compact and semantically sparse manifold. Then, during sampling time, we abandon the flawed sequential sampling paradigm and instead synchronously denoises the entire synthetic dataset with distribution regularizers. This framework systematically mitigates both identified distribution shifts. Experiments show our method achieves state-of-the-art performance with superior computational efficiency.