Ye Pan

Teng Hu, Mingchun Lu, Yating Wang et al.

Video world models are a foundational generative technology for embodied AI and the Metaverse, yet existing approaches are inherently limited to a single agent observing from a single perspective. Extending these models to multi-agent settings introduces two critical challenges: data scarcity (coordinated multi-view recordings are prohibitively expensive to collect for general open-domain scenarios) and world state alignment (independently generated video streams cannot ensure that shared physical environments and events evolve consistently across views). To address these challenges, we propose MetaWorld, a novel framework that scales multi-agent video world models to open-domain environments directly from single-view videos. First, we introduce Monocular World-State Unrolling (MWSU) to explicitly decompose monocular footage into the camera operator's ego-motion and the visible subject's spatial trajectory. This camera-trajectory decomposition naturally extracts synchronized multi-agent motion data within a shared 3D space, completely bypassing the need for multi-camera setups. Second, for precise visual control, we develop the Subject-Aware World Generator to enable appearance-driven simulation conditioned on per-agent identity images. Finally, to ensure both views are grounded in the identical physical reality, we propose World-State Alignment, a per-frame inter-branch cross-attention mechanism inserted at every transformer layer of the video DiT. By jointly synchronizing the denoising process, WSA enforces both static geometric consistency and dynamic motion consistency, encouraging that the shared 3D environment and physical events remain well-aligned across both egocentric views. Extensive experiments demonstrate that MetaWorld achieves superior cross-view consistency and identity fidelity, establishing a highly scalable, physics-driven paradigm for multi-agent video world modeling.

Yuhao Cheng, Yichao Yan, Wenhan Zhu et al.

Head generation with diverse identities is an important task in computer vision and computer graphics, widely used in multimedia applications. However, current full head generation methods require a large number of 3D scans or multi-view images to train the model, resulting in expensive data acquisition cost. To address this issue, we propose Head3D, a method to generate full 3D heads with limited multi-view images. Specifically, our approach first extracts facial priors represented by tri-planes learned in EG3D, a 3D-aware generative model, and then proposes feature distillation to deliver the 3D frontal faces into complete heads without compromising head integrity. To mitigate the domain gap between the face and head models, we present dual-discriminators to guide the frontal and back head generation, respectively. Our model achieves cost-efficient and diverse complete head generation with photo-realistic renderings and high-quality geometry representations. Extensive experiments demonstrate the effectiveness of our proposed Head3D, both qualitatively and quantitatively.

Zhuo Chen, Xudong Xu, Yichao Yan et al.

Portrait stylization is a long-standing task enabling extensive applications. Although 2D-based methods have made great progress in recent years, real-world applications such as metaverse and games often demand 3D content. On the other hand, the requirement of 3D data, which is costly to acquire, significantly impedes the development of 3D portrait stylization methods. In this paper, inspired by the success of 3D-aware GANs that bridge 2D and 3D domains with 3D fields as the intermediate representation for rendering 2D images, we propose a novel method, dubbed HyperStyle3D, based on 3D-aware GANs for 3D portrait stylization. At the core of our method is a hyper-network learned to manipulate the parameters of the generator in a single forward pass. It not only offers a strong capacity to handle multiple styles with a single model, but also enables flexible fine-grained stylization that affects only texture, shape, or local part of the portrait. While the use of 3D-aware GANs bypasses the requirement of 3D data, we further alleviate the necessity of style images with the CLIP model being the stylization guidance. We conduct an extensive set of experiments across the style, attribute, and shape, and meanwhile, measure the 3D consistency. These experiments demonstrate the superior capability of our HyperStyle3D model in rendering 3D-consistent images in diverse styles, deforming the face shape, and editing various attributes.

Ye Pan, Chi Kit Wong, Yuanhuiyi Lyu et al.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable video reasoning capabilities across diverse tasks. However, their ability to understand human intent at a fine-grained level in egocentric videos remains largely unexplored. Existing benchmarks focus primarily on episode-level intent reasoning, overlooking the finer granularity of step-level intent understanding. Yet applications such as intelligent assistants, robotic imitation learning, and augmented reality guidance require understanding not only what a person is doing at each step, but also why and what comes next, in order to provide timely and context-aware support. To this end, we introduce EgoIntent, a step-level intent understanding benchmark for egocentric videos. It comprises 3,014 steps spanning 15 diverse indoor and outdoor daily-life scenarios, and evaluates models on three complementary dimensions: local intent (What), global intent (Why), and next-step plan (Next). Crucially, each clip is truncated immediately before the key outcome of the queried step (e.g., contact or grasp) occurs and contains no frames from subsequent steps, preventing future-frame leakage and enabling a clean evaluation of anticipatory step understanding and next-step planning. We evaluate 15 MLLMs, including both state-of-the-art closed-source and open-source models. Even the best-performing model achieves an average score of only 33.31 across the three intent dimensions, underscoring that step-level intent understanding in egocentric videos remains a highly challenging problem that calls for further investigation.

Jiahao Huo, Yu Huang, Yibo Yan et al.

Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the substantial storage overhead caused by representing a page with thousands of visual tokens limits their practicality in real-world applications. To address this challenge, we propose an auto-regressive generation approach, CausalEmbed, for constructing multi-vector embeddings. By incorporating iterative margin loss during contrastive training, CausalEmbed encourages the embedding models to learn compact and well-structured representations. Our method enables efficient VDR tasks using only dozens of visual tokens, achieving a 30-155x reduction in token count while maintaining highly competitive performance across various backbones and benchmarks. Theoretical analysis and empirical results demonstrate the unique advantages of auto-regressive embedding generation in terms of training efficiency and scalability at test time. As a result, CausalEmbed introduces a flexible test-time scaling strategy for multi-vector VDR representations and sheds light on the generative paradigm within multimodal document retrieval. Our code is available at https://github.com/Z1zs/Causal-Embed.

Chang Liu, Qunfen Lin, Zijiao Zeng et al.

Audio-driven emotional 3D face animation aims to generate emotionally expressive talking heads with synchronized lip movements. However, previous research has often overlooked the influence of diverse emotions on facial expressions or proved unsuitable for driving MetaHuman models. In response to this deficiency, we introduce EmoFace, a novel audio-driven methodology for creating facial animations with vivid emotional dynamics. Our approach can generate facial expressions with multiple emotions, and has the ability to generate random yet natural blinks and eye movements, while maintaining accurate lip synchronization. We propose independent speech encoders and emotion encoders to learn the relationship between audio, emotion and corresponding facial controller rigs, and finally map into the sequence of controller values. Additionally, we introduce two post-processing techniques dedicated to enhancing the authenticity of the animation, particularly in blinks and eye movements. Furthermore, recognizing the scarcity of emotional audio-visual data suitable for MetaHuman model manipulation, we contribute an emotional audio-visual dataset and derive control parameters for each frames. Our proposed methodology can be applied in producing dialogues animations of non-playable characters (NPCs) in video games, and driving avatars in virtual reality environments. Our further quantitative and qualitative experiments, as well as an user study comparing with existing researches show that our approach demonstrates superior results in driving 3D facial models. The code and sample data are available at https://github.com/SJTU-Lucy/EmoFace.

Hanqian Li, Ruinan Zhang, Ye Pan et al.

Remote sensing target detection aims to identify and locate critical targets within remote sensing images, finding extensive applications in agriculture and urban planning. Feature pyramid networks (FPNs) are commonly used to extract multi-scale features. However, existing FPNs often overlook extracting low-level positional information and fine-grained context interaction. To address this, we propose a novel location refined feature pyramid network (LR-FPN) to enhance the extraction of shallow positional information and facilitate fine-grained context interaction. The LR-FPN consists of two primary modules: the shallow position information extraction module (SPIEM) and the contextual interaction module (CIM). Specifically, SPIEM first maximizes the retention of solid location information of the target by simultaneously extracting positional and saliency information from the low-level feature map. Subsequently, CIM injects this robust location information into different layers of the original FPN through spatial and channel interaction, explicitly enhancing the object area. Moreover, in spatial interaction, we introduce a simple local and non-local interaction strategy to learn and retain the saliency information of the object. Lastly, the LR-FPN can be readily integrated into common object detection frameworks to improve performance significantly. Extensive experiments on two large-scale remote sensing datasets (i.e., DOTAV1.0 and HRSC2016) demonstrate that the proposed LR-FPN is superior to state-of-the-art object detection approaches. Our code and models will be publicly available.

Shaoxu Li, Ye Pan

In this paper, we propose a method that enables interactive geometry editing for neural radiance fields manipulation. We use two proxy cages(inner cage and outer cage) to edit a scene. The inner cage defines the operation target, and the outer cage defines the adjustment space. Various operations apply to the two cages. After cage selection, operations on the inner cage lead to the desired transformation of the inner cage and adjustment of the outer cage. Users can edit the scene with translation, rotation, scaling, or combinations. The operations on the corners and edges of the cage are also supported. Our method does not need any explicit 3D geometry representations. The interactive geometry editing applies directly to the implicit neural radiance fields. Extensive experimental results demonstrate the effectiveness of our approach.

Chuhang Ma, Shuai Tan, Ye Pan et al.

Most current audio-driven facial animation research primarily focuses on generating videos with neutral emotions. While some studies have addressed the generation of facial videos driven by emotional audio, efficiently generating high-quality talking head videos that integrate both emotional expressions and style features remains a significant challenge. In this paper, we propose ESGaussianFace, an innovative framework for emotional and stylized audio-driven facial animation. Our approach leverages 3D Gaussian Splatting to reconstruct 3D scenes and render videos, ensuring efficient generation of 3D consistent results. We propose an emotion-audio-guided spatial attention method that effectively integrates emotion features with audio content features. Through emotion-guided attention, the model is able to reconstruct facial details across different emotional states more accurately. To achieve emotional and stylized deformations of the 3D Gaussian points through emotion and style features, we introduce two 3D Gaussian deformation predictors. Futhermore, we propose a multi-stage training strategy, enabling the step-by-step learning of the character's lip movements, emotional variations, and style features. Our generated results exhibit high efficiency, high quality, and 3D consistency. Extensive experimental results demonstrate that our method outperforms existing state-of-the-art techniques in terms of lip movement accuracy, expression variation, and style feature expressiveness.

Shaoxu Li, Ye Pan

We present Instant Neural Radiance Fields Stylization, a novel approach for multi-view image stylization for the 3D scene. Our approach models a neural radiance field based on neural graphics primitives, which use a hash table-based position encoder for position embedding. We split the position encoder into two parts, the content and style sub-branches, and train the network for normal novel view image synthesis with the content and style targets. In the inference stage, we execute AdaIN to the output features of the position encoder, with content and style voxel grid features as reference. With the adjusted features, the stylization of novel view images could be obtained. Our method extends the style target from style images to image sets of scenes and does not require additional network training for stylization. Given a set of images of 3D scenes and a style target(a style image or another set of 3D scenes), our method can generate stylized novel views with a consistent appearance at various view angles in less than 10 minutes on modern GPU hardware. Extensive experimental results demonstrate the validity and superiority of our method.

Chang Liu, Ye Pan, Chenyang Ding et al.

Audio-driven emotional 3D facial animation aims to generate synchronized lip movements and vivid facial expressions. However, most existing approaches focus on static and predefined emotion labels, limiting their diversity and naturalness. To address these challenges, we propose MEDTalk, a novel framework for fine-grained and dynamic emotional talking head generation. Our approach first disentangles content and emotion embedding spaces from motion sequences using a carefully designed cross-reconstruction process, enabling independent control over lip movements and facial expressions. Beyond conventional audio-driven lip synchronization, we integrate audio and speech text, predicting frame-wise intensity variations and dynamically adjusting static emotion features to generate realistic emotional expressions. Furthermore, to enhance control and personalization, we incorporate multimodal inputs-including text descriptions and reference expression images-to guide the generation of user-specified facial expressions. With MetaHuman as the priority, our generated results can be conveniently integrated into the industrial production pipeline. The code is available at: https://github.com/SJTU-Lucy/MEDTalk.

Shuai Tan, Bin Ji, Mengxiao Bi et al.

Achieving disentangled control over multiple facial motions and accommodating diverse input modalities greatly enhances the application and entertainment of the talking head generation. This necessitates a deep exploration of the decoupling space for facial features, ensuring that they a) operate independently without mutual interference and b) can be preserved to share with different modal input, both aspects often neglected in existing methods. To address this gap, this paper proposes a novel Efficient Disentanglement framework for Talking head generation (EDTalk). Our framework enables individual manipulation of mouth shape, head pose, and emotional expression, conditioned on video or audio inputs. Specifically, we employ three lightweight modules to decompose the facial dynamics into three distinct latent spaces representing mouth, pose, and expression, respectively. Each space is characterized by a set of learnable bases whose linear combinations define specific motions. To ensure independence and accelerate training, we enforce orthogonality among bases and devise an efficient training strategy to allocate motion responsibilities to each space without relying on external knowledge. The learned bases are then stored in corresponding banks, enabling shared visual priors with audio input. Furthermore, considering the properties of each space, we propose an Audio-to-Motion module for audio-driven talking head synthesis. Experiments are conducted to demonstrate the effectiveness of EDTalk. We recommend watching the project website: https://tanshuai0219.github.io/EDTalk/

Shuai Tan, Bin Ji, Ye Pan

Although automatically animating audio-driven talking heads has recently received growing interest, previous efforts have mainly concentrated on achieving lip synchronization with the audio, neglecting two crucial elements for generating expressive videos: emotion style and art style. In this paper, we present an innovative audio-driven talking face generation method called Style2Talker. It involves two stylized stages, namely Style-E and Style-A, which integrate text-controlled emotion style and picture-controlled art style into the final output. In order to prepare the scarce emotional text descriptions corresponding to the videos, we propose a labor-free paradigm that employs large-scale pretrained models to automatically annotate emotional text labels for existing audiovisual datasets. Incorporating the synthetic emotion texts, the Style-E stage utilizes a large-scale CLIP model to extract emotion representations, which are combined with the audio, serving as the condition for an efficient latent diffusion model designed to produce emotional motion coefficients of a 3DMM model. Moving on to the Style-A stage, we develop a coefficient-driven motion generator and an art-specific style path embedded in the well-known StyleGAN. This allows us to synthesize high-resolution artistically stylized talking head videos using the generated emotional motion coefficients and an art style source picture. Moreover, to better preserve image details and avoid artifacts, we provide StyleGAN with the multi-scale content features extracted from the identity image and refine its intermediate feature maps by the designed content encoder and refinement network, respectively. Extensive experimental results demonstrate our method outperforms existing state-of-the-art methods in terms of audio-lip synchronization and performance of both emotion style and art style.

Shuai Tan, Bin Ji, Ye Pan

Generating emotional talking faces is a practical yet challenging endeavor. To create a lifelike avatar, we draw upon two critical insights from a human perspective: 1) The connection between audio and the non-deterministic facial dynamics, encompassing expressions, blinks, poses, should exhibit synchronous and one-to-many mapping. 2) Vibrant expressions are often accompanied by emotion-aware high-definition (HD) textures and finely detailed teeth. However, both aspects are frequently overlooked by existing methods. To this end, this paper proposes using normalizing Flow and Vector-Quantization modeling to produce emotional talking faces that satisfy both insights concurrently (FlowVQTalker). Specifically, we develop a flow-based coefficient generator that encodes the dynamics of facial emotion into a multi-emotion-class latent space represented as a mixture distribution. The generation process commences with random sampling from the modeled distribution, guided by the accompanying audio, enabling both lip-synchronization and the uncertain nonverbal facial cues generation. Furthermore, our designed vector-quantization image generator treats the creation of expressive facial images as a code query task, utilizing a learned codebook to provide rich, high-quality textures that enhance the emotional perception of the results. Extensive experiments are conducted to showcase the effectiveness of our approach.

Shuai Tan, Bin Ji, Yu Ding et al.

Generating stylized talking head with diverse head motions is crucial for achieving natural-looking videos but still remains challenging. Previous works either adopt a regressive method to capture the speaking style, resulting in a coarse style that is averaged across all training data, or employ a universal network to synthesize videos with different styles which causes suboptimal performance. To address these, we propose a novel dynamic-weight method, namely Say Anything withAny Style (SAAS), which queries the discrete style representation via a generative model with a learned style codebook. Specifically, we develop a multi-task VQ-VAE that incorporates three closely related tasks to learn a style codebook as a prior for style extraction. This discrete prior, along with the generative model, enhances the precision and robustness when extracting the speaking styles of the given style clips. By utilizing the extracted style, a residual architecture comprising a canonical branch and style-specific branch is employed to predict the mouth shapes conditioned on any driving audio while transferring the speaking style from the source to any desired one. To adapt to different speaking styles, we steer clear of employing a universal network by exploring an elaborate HyperStyle to produce the style-specific weights offset for the style branch. Furthermore, we construct a pose generator and a pose codebook to store the quantized pose representation, allowing us to sample diverse head motions aligned with the audio and the extracted style. Experiments demonstrate that our approach surpasses state-of-theart methods in terms of both lip-synchronization and stylized expression. Besides, we extend our SAAS to video-driven style editing field and achieve satisfactory performance.

Shuai Tan, Bill Gong, Bin Ji et al.

Talking head generation is gaining significant importance across various domains, with a growing demand for high-quality rendering. However, existing methods often suffer from identity leakage (IL) and rendering artifacts (RA), particularly in extreme cases. Through an in-depth analysis of previous approaches, we identify two key insights: (1) IL arises from identity information embedded within motion features, and (2) this identity information can be leveraged to address RA. Building on these findings, this paper introduces FixTalk, a novel framework designed to simultaneously resolve both issues for high-quality talking head generation. Firstly, we propose an Enhanced Motion Indicator (EMI) to effectively decouple identity information from motion features, mitigating the impact of IL on generated talking heads. To address RA, we introduce an Enhanced Detail Indicator (EDI), which utilizes the leaked identity information to supplement missing details, thus fixing the artifacts. Extensive experiments demonstrate that FixTalk effectively mitigates IL and RA, achieving superior performance compared to state-of-the-art methods.

Yanwen Zou, Chenyang Shi, Wenye Yu et al.

Large-scale real-world robot data collection is a prerequisite for bringing robots into everyday deployment. However, existing pipelines often rely on specialized handheld devices to bridge the embodiment gap, which not only increases operator burden and limits scalability, but also makes it difficult to capture the naturally coordinated perception-manipulation behaviors of human daily interaction. This challenge calls for a more natural system that can faithfully capture human manipulation and perception behaviors while enabling zero-shot transfer to robotic platforms. We introduce ActiveGlasses, a system for learning robot manipulation from ego-centric human demonstrations with active vision. A stereo camera mounted on smart glasses serves as the sole perception device for both data collection and policy inference: the operator wears it during bare-hand demonstrations, and the same camera is mounted on a 6-DoF perception arm during deployment to reproduce human active vision. To enable zero-transfer, we extract object trajectories from demonstrations and use an object-centric point-cloud policy to jointly predict manipulation and head movement. Across several challenging tasks involving occlusion and precise interaction, ActiveGlasses achieves zero-shot transfer with active vision, consistently outperforms strong baselines under the same hardware setup, and generalizes across two robot platforms.

Ye Pan, Ruisi Zhang, Jingying Wang et al.

Our purpose is to improve performance-based animation which can drive believable 3D stylized characters that are truly perceptual. By combining traditional blendshape animation techniques with multiple machine learning models, we present both non-real time and real time solutions which drive character expressions in a geometrically consistent and perceptually valid way. For the non-real time system, we propose a 3D emotion transfer network makes use of a 2D human image to generate a stylized 3D rig parameters. For the real time system, we propose a blendshape adaption network which generates the character rig parameter motions with geometric consistency and temporally stability. We demonstrate the effectiveness of our system by comparing to a commercial product Faceware. Results reveal that ratings of the recognition, intensity, and attractiveness of expressions depicted for animated characters via our systems are statistically higher than Faceware. Our results may be implemented into the animation pipeline, and provide animators with a system for creating the expressions they wish to use more quickly and accurately.

Huixu Dong, Chen Qiu, Dilip K. Prasad et al.

Performing a grasp is a pivotal capability for a robotic gripper. We propose a new evaluation approach of grasping stability via constructing a model of grasping stiffness based on the theory of contact mechanics. First, the mathematical models are built to explore soft contact and the general grasp stiffness between a finger and an object. Next, the grasping stiffness matrix is constructed to reflect the normal, tangential and torsion stiffness coefficients. Finally, we design two grasping cases to verify the proposed measurement criterion of grasping stability by comparing different grasping configurations. Specifically, a standard grasping index is used and compared with the minimum eigenvalue index of the constructed grasping stiffness we built. The comparison result reveals a similar tendency between them for measuring the grasping stability and thus, validates the proposed approach.

Weinan Zhang, Ye Pan, Tianxiong Zhou et al.

Display advertising normally charges advertisers for every single ad impression. Specifically, if an ad in a webpage has been loaded in the browser, an ad impression is counted. However, due to the position and size of the ad slot, lots of ads are actually not viewed but still measured as impressions and charged. These fraud ad impressions indeed undermine the efficacy of display advertising. A perfect ad impression viewability measurement should match what the user has really viewed with a short memory. In this paper, we conduct extensive investigations on display ad impression viewability measurements on dimensions of ad creative displayed pixel percentage and exposure time to find which measurement provides the most accurate ad impression counting. The empirical results show that the most accurate measurement counts one ad impression if more than 75% of the ad creative pixels have been exposed for at least 2 continuous seconds.