Zhenzhi Wang

Yixuan Li, Lihan Jiang, Linning Xu et al.

Neural radiance fields (NeRF) and its subsequent variants have led to remarkable progress in neural rendering. While most of recent neural rendering works focus on objects and small-scale scenes, developing neural rendering methods for city-scale scenes is of great potential in many real-world applications. However, this line of research is impeded by the absence of a comprehensive and high-quality dataset, yet collecting such a dataset over real city-scale scenes is costly, sensitive, and technically difficult. To this end, we build a large-scale, comprehensive, and high-quality synthetic dataset for city-scale neural rendering researches. Leveraging the Unreal Engine 5 City Sample project, we develop a pipeline to easily collect aerial and street city views, accompanied by ground-truth camera poses and a range of additional data modalities. Flexible controls over environmental factors like light, weather, human and car crowd are also available in our pipeline, supporting the need of various tasks covering city-scale neural rendering and beyond. The resulting pilot dataset, MatrixCity, contains 67k aerial images and 452k street images from two city maps of total size $28km^2$. On top of MatrixCity, a thorough benchmark is also conducted, which not only reveals unique challenges of the task of city-scale neural rendering, but also highlights potential improvements for future works. The dataset and code will be publicly available at our project page: https://city-super.github.io/matrixcity/.

Zhenzhi Wang, Jingbo Wang, Yixuan Li et al.

Text-conditioned motion synthesis has made remarkable progress with the emergence of diffusion models. However, the majority of these motion diffusion models are primarily designed for a single character and overlook multi-human interactions. In our approach, we strive to explore this problem by synthesizing human motion with interactions for a group of characters of any size in a zero-shot manner. The key aspect of our approach is the adaptation of human-wise interactions as pairs of human joints that can be either in contact or separated by a desired distance. In contrast to existing methods that necessitate training motion generation models on multi-human motion datasets with a fixed number of characters, our approach inherently possesses the flexibility to model human interactions involving an arbitrary number of individuals, thereby transcending the limitations imposed by the training data. We introduce a novel controllable motion generation method, InterControl, to encourage the synthesized motions maintaining the desired distance between joint pairs. It consists of a motion controller and an inverse kinematics guidance module that realistically and accurately aligns the joints of synthesized characters to the desired location. Furthermore, we demonstrate that the distance between joint pairs for human-wise interactions can be generated using an off-the-shelf Large Language Model (LLM). Experimental results highlight the capability of our framework to generate interactions with multiple human characters and its potential to work with off-the-shelf physics-based character simulators. Code is available at https://github.com/zhenzhiwang/intercontrol

Zhenzhi Wang, Yixuan Li, Yanhong Zeng et al.

Human image animation involves generating videos from a character photo, allowing user control and unlocking the potential for video and movie production. While recent approaches yield impressive results using high-quality training data, the inaccessibility of these datasets hampers fair and transparent benchmarking. Moreover, these approaches prioritize 2D human motion and overlook the significance of camera motions in videos, leading to limited control and unstable video generation. To demystify the training data, we present HumanVid, the first large-scale high-quality dataset tailored for human image animation, which combines crafted real-world and synthetic data. For the real-world data, we compile a vast collection of real-world videos from the internet. We developed and applied careful filtering rules to ensure video quality, resulting in a curated collection of 20K high-resolution (1080P) human-centric videos. Human and camera motion annotation is accomplished using a 2D pose estimator and a SLAM-based method. To expand our synthetic dataset, we collected 10K 3D avatar assets and leveraged existing assets of body shapes, skin textures and clothings. Notably, we introduce a rule-based camera trajectory generation method, enabling the synthetic pipeline to incorporate diverse and precise camera motion annotation, which can rarely be found in real-world data. To verify the effectiveness of HumanVid, we establish a baseline model named CamAnimate, short for Camera-controllable Human Animation, that considers both human and camera motions as conditions. Through extensive experimentation, we demonstrate that such simple baseline training on our HumanVid achieves state-of-the-art performance in controlling both human pose and camera motions, setting a new benchmark. Demo, data and code could be found in the project website: https://humanvid.github.io/.

Zhenzhi Wang, Jian Wang, Ke Ma et al.

We introduce TalkVerse, a large-scale, open corpus for single-person, audio-driven talking video generation designed to enable fair, reproducible comparison across methods. While current state-of-the-art systems rely on closed data or compute-heavy models, TalkVerse offers 2.3 million high-resolution (720p/1080p) audio-video synchronized clips totaling 6.3k hours. These are curated from over 60k hours of video via a transparent pipeline that includes scene-cut detection, aesthetic assessment, strict audio-visual synchronization checks, and comprehensive annotations including 2D skeletons and structured visual/audio-style captions. Leveraging TalkVerse, we present a reproducible 5B DiT baseline built on Wan2.2-5B. By utilizing a video VAE with a high downsampling ratio and a sliding window mechanism with motion-frame context, our model achieves minute-long generation with low drift. It delivers comparable lip-sync and visual quality to the 14B Wan-S2V model but with 10$\times$ lower inference cost. To enhance storytelling in long videos, we integrate an MLLM director to rewrite prompts based on audio and visual cues. Furthermore, our model supports zero-shot video dubbing via controlled latent noise injection. We open-source the dataset, training recipes, and 5B checkpoints to lower barriers for research in audio-driven human video generation. Project Page: https://zhenzhiwang.github.io/talkverse/

Zhenzhi Wang, Yixuan Li, Yanhong Zeng et al.

Generating human videos from a single image while ensuring high visual quality and precise control is a challenging task, especially in complex scenarios involving multiple individuals and interactions with objects. Existing methods, while effective for single-human cases, often fail to handle the intricacies of multi-identity interactions because they struggle to associate the correct pairs of human appearance and pose condition and model the distribution of 3D-aware dynamics. To address these limitations, we present \emph{Structural Video Diffusion}, a novel framework designed for generating realistic multi-human videos. Our approach introduces two core innovations: identity-specific embeddings to maintain consistent appearances across individuals and a structural learning mechanism that incorporates depth and surface-normal cues to model human-object interactions. Additionally, we expand existing human video dataset with 25K new videos featuring diverse multi-human and object interaction scenarios, providing a robust foundation for training. Experimental results demonstrate that Structural Video Diffusion achieves superior performance in generating lifelike, coherent videos for multiple subjects with dynamic and rich interactions, advancing the state of human-centric video generation. Code is available at https://github.com/zhenzhiwang/Multi-HumanVid

Zhenzhi Wang, Limin Wang, Tao Wu et al.

Temporal grounding aims to localize a video moment which is semantically aligned with a given natural language query. Existing methods typically apply a detection or regression pipeline on the fused representation with the research focus on designing complicated prediction heads or fusion strategies. Instead, from a perspective on temporal grounding as a metric-learning problem, we present a Mutual Matching Network (MMN), to directly model the similarity between language queries and video moments in a joint embedding space. This new metric-learning framework enables fully exploiting negative samples from two new aspects: constructing negative cross-modal pairs in a mutual matching scheme and mining negative pairs across different videos. These new negative samples could enhance the joint representation learning of two modalities via cross-modal mutual matching to maximize their mutual information. Experiments show that our MMN achieves highly competitive performance compared with the state-of-the-art methods on four video grounding benchmarks. Based on MMN, we present a winner solution for the HC-STVG challenge of the 3rd PIC workshop. This suggests that metric learning is still a promising method for temporal grounding via capturing the essential cross-modal correlation in a joint embedding space. Code is available at https://github.com/MCG-NJU/MMN.

Yixuan Li, Xingjian Ran, Linning Xu et al.

Buildings are primary components of cities, often featuring repeated elements such as windows and doors. Traditional 3D building asset creation is labor-intensive and requires specialized skills to develop design rules. Recent generative models for building creation often overlook these patterns, leading to low visual fidelity and limited scalability. Drawing inspiration from procedural modeling techniques used in the gaming and visual effects industry, our method, Proc-GS, integrates procedural code into the 3D Gaussian Splatting (3D-GS) framework, leveraging their advantages in high-fidelity rendering and efficient asset management from both worlds. By manipulating procedural code, we can streamline this process and generate an infinite variety of buildings. This integration significantly reduces model size by utilizing shared foundational assets, enabling scalable generation with precise control over building assembly. We showcase the potential for expansive cityscape generation while maintaining high rendering fidelity and precise control on both real and synthetic cases.

Zhenzhi Wang, Jiaqi Yang, Jianwen Jiang et al.

End-to-end human animation with rich multi-modal conditions, e.g., text, image and audio has achieved remarkable advancements in recent years. However, most existing methods could only animate a single subject and inject conditions in a global manner, ignoring scenarios that multiple concepts could appears in the same video with rich human-human interactions and human-object interactions. Such global assumption prevents precise and per-identity control of multiple concepts including humans and objects, therefore hinders applications. In this work, we discard the single-entity assumption and introduce a novel framework that enforces strong, region-specific binding of conditions from modalities to each identity's spatiotemporal footprint. Given reference images of multiple concepts, our method could automatically infer layout information by leveraging a mask predictor to match appearance cues between the denoised video and each reference appearance. Furthermore, we inject local audio condition into its corresponding region to ensure layout-aligned modality matching in a iterative manner. This design enables the high-quality generation of controllable multi-concept human-centric videos. Empirical results and ablation studies validate the effectiveness of our explicit layout control for multi-modal conditions compared to implicit counterparts and other existing methods.

Zhenzhi Wang, Liyu Wu, Zhimin Li et al.

Multi-modal Ads Video Understanding Challenge is the first grand challenge aiming to comprehensively understand ads videos. Our challenge includes two tasks: video structuring in the temporal dimension and multi-modal video classification. It asks the participants to accurately predict both the scene boundaries and the multi-label categories of each scene based on a fine-grained and ads-related category hierarchy. Therefore, our task has four distinguishing features from previous ones: ads domain, multi-modal information, temporal segmentation, and multi-label classification. It will advance the foundation of ads video understanding and have a significant impact on many ads applications like video recommendation. This paper presents an overview of our challenge, including the background of ads videos, an elaborate description of task and dataset, evaluation protocol, and our proposed baseline. By ablating the key components of our baseline, we would like to reveal the main challenges of this task and provide useful guidance for future research of this area. In this paper, we give an extended version of our challenge overview. The dataset will be publicly available at https://algo.qq.com/.

Yixuan Li, Lei Chen, Runyu He et al.

Spatio-temporal action detection is an important and challenging problem in video understanding. The existing action detection benchmarks are limited in aspects of small numbers of instances in a trimmed video or low-level atomic actions. This paper aims to present a new multi-person dataset of spatio-temporal localized sports actions, coined as MultiSports. We first analyze the important ingredients of constructing a realistic and challenging dataset for spatio-temporal action detection by proposing three criteria: (1) multi-person scenes and motion dependent identification, (2) with well-defined boundaries, (3) relatively fine-grained classes of high complexity. Based on these guide-lines, we build the dataset of MultiSports v1.0 by selecting 4 sports classes, collecting 3200 video clips, and annotating 37701 action instances with 902k bounding boxes. Our datasets are characterized with important properties of high diversity, dense annotation, and high quality. Our Multi-Sports, with its realistic setting and detailed annotations, exposes the intrinsic challenges of spatio-temporal action detection. To benchmark this, we adapt several baseline methods to our dataset and give an in-depth analysis on the action detection results in our dataset. We hope our MultiSports can serve as a standard benchmark for spatio-temporal action detection in the future. Our dataset website is at https://deeperaction.github.io/multisports/.