中文
相关论文

相关论文: SINC: Spatial Composition of 3D Human Motions for …

200 篇论文

Text-to-motion synthesis is a crucial task in computer vision. Existing methods are limited in their universality, as they are tailored for single-person or two-person scenarios and can not be applied to generate motions for more…

计算机视觉与模式识别 · 计算机科学 2024-05-27 Ke Fan , Junshu Tang , Weijian Cao , Ran Yi , Moran Li , Jingyu Gong , Jiangning Zhang , Yabiao Wang , Chengjie Wang , Lizhuang Ma

3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent…

图形学 · 计算机科学 2026-05-20 Yi-Yang Zhang , Tengjiao Sun , Pengcheng Fang , Deng-Bao Wang , Xiaohao Cai , Min-Ling Zhang , Hansung Kim

Advances in the state of the art for 3d human sensing are currently limited by the lack of visual datasets with 3d ground truth, including multiple people, in motion, operating in real-world environments, with complex illumination or…

计算机视觉与模式识别 · 计算机科学 2022-01-07 Eduard Gabriel Bazavan , Andrei Zanfir , Mihai Zanfir , William T. Freeman , Rahul Sukthankar , Cristian Sminchisescu

The focus of the action understanding literature has predominately been classification, how- ever, there are many applications demanding richer action understanding such as mobile robotics and video search, with solutions to classification,…

计算机视觉与模式识别 · 计算机科学 2014-10-23 Ran Xu , Gang Chen , Caiming Xiong , Wei Chen , Jason J. Corso

Large-scale articulated objects with high quality are desperately needed for multiple tasks related to embodied AI. Most existing methods for creating articulated objects are either data-driven or simulation based, which are limited by the…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Xinyu Lian , Zichao Yu , Ruiming Liang , Yitong Wang , Li Ray Luo , Kaixu Chen , Yuanzhen Zhou , Qihong Tang , Xudong Xu , Zhaoyang Lyu , Bo Dai , Jiangmiao Pang

DuctTake is a system designed to enable practical compositing of multiple takes of a scene into a single video. Current industry solutions are based around object segmentation, a hard problem that requires extensive manual input and…

计算机视觉与模式识别 · 计算机科学 2021-01-14 Jan Rueegg , Oliver Wang , Aljoscha Smolic , Markus Gross

Text-to-motion generation has advanced rapidly, yet two challenges persist. First, existing motion autoencoders compress each frame into a single monolithic latent vector, entangling trajectory and per-joint rotations in an unstructured…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Zeyu Ling , Qing Shuai , Teng Zhang , Shiyang Li , Bo Han , Changqing Zou

High fidelity digital 3D environments have been proposed in recent years, however, it remains extremely challenging to automatically equip such environment with realistic human bodies. Existing work utilizes images, depth or semantic maps…

计算机视觉与模式识别 · 计算机科学 2020-11-13 Siwei Zhang , Yan Zhang , Qianli Ma , Michael J. Black , Siyu Tang

Synthesizing human motions in 3D environments, particularly those with complex activities such as locomotion, hand-reaching, and human-object interaction, presents substantial demands for user-defined waypoints and stage transitions. These…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Nan Jiang , Zimo He , Zi Wang , Hongjie Li , Yixin Chen , Siyuan Huang , Yixin Zhu

The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in customizable image synthesis. However, achieving controllable video synthesis remains challenging due to the large variation…

计算机视觉与模式识别 · 计算机科学 2023-06-07 Xiang Wang , Hangjie Yuan , Shiwei Zhang , Dayou Chen , Jiuniu Wang , Yingya Zhang , Yujun Shen , Deli Zhao , Jingren Zhou

The ability to synthesize long-term human motion sequences in real-world scenes can facilitate numerous applications. Previous approaches for scene-aware motion synthesis are constrained by pre-defined target objects or positions and thus…

计算机视觉与模式识别 · 计算机科学 2022-05-27 Jingbo Wang , Yu Rong , Jingyuan Liu , Sijie Yan , Dahua Lin , Bo Dai

Embodied human communication encompasses both verbal (speech) and non-verbal information (e.g., gesture and head movements). Recent advances in machine learning have substantially improved the technologies for generating synthetic versions…

机器学习 · 计算机科学 2021-01-15 Simon Alexanderson , Éva Székely , Gustav Eje Henter , Taras Kucherenko , Jonas Beskow

In this paper, we propose a novel framework, Combo, for harmonious co-speech holistic 3D human motion generation and efficient customizable adaption. In particular, we identify that one fundamental challenge as the…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Chao Xu , Mingze Sun , Zhi-Qi Cheng , Fei Wang , Yang Liu , Baigui Sun , Ruqi Huang , Alexander Hauptmann

Generating human motions from textual descriptions has gained growing research interest due to its wide range of applications. However, only a few works consider human-scene interactions together with text conditions, which is crucial for…

计算机视觉与模式识别 · 计算机科学 2024-05-14 Zhi Cen , Huaijin Pi , Sida Peng , Zehong Shen , Minghui Yang , Shuai Zhu , Hujun Bao , Xiaowei Zhou

Trajectory-controlled human motion generation aims to synthesize realistic human motions conditioned on both textual descriptions and spatial trajectories. However, existing methods suffer from two critical limitations: first, the conflict…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Deli Cai , Haoyang Ma , Changxing Ding

This report reviews recent advancements in human motion prediction, reconstruction, and generation. Human motion prediction focuses on forecasting future poses and movements from historical data, addressing challenges like nonlinear…

计算机视觉与模式识别 · 计算机科学 2025-02-25 Canxuan Gang , Yiran Wang

Synthesizing realistic human-object interaction motions is a critical problem in VR/AR and human animation. Unlike the commonly studied scenarios involving a single human or hand interacting with one object, we address a more generic…

计算机视觉与模式识别 · 计算机科学 2025-07-31 Wenkun He , Yun Liu , Ruitao Liu , Li Yi

Millions of surveillance cameras operate at 24x7 generating huge amount of visual data for processing. However, retrieval of important activities from such a large data can be time consuming. Thus, researchers are working on finding…

计算机视觉与模式识别 · 计算机科学 2017-09-18 A. Ahmed , D. P. Dogra , S. Kar , R. Patnaik , S. Lee , H. Choi , I. Kim

Human motions are compositional: complex behaviors can be described as combinations of simpler primitives. However, existing approaches primarily focus on forward modeling, e.g., learning holistic mappings from text to motion or composing a…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Jianrong Zhang , Hehe Fan , Yi Yang

Creating and editing high-quality 3D content remains a central challenge in computer graphics. We address this challenge by introducing CompoSE, a novel method for Compositional Synthesis and Editing of 3D shapes via part-aware control. Our…

图形学 · 计算机科学 2026-05-20 Habib Slim , Shariq Farooq Bhat , Mohamed Elhoseiny , Yifan Wang , Mike Roberts