中文
相关论文

相关论文: OmniControl: Control Any Joint at Any Time for Hum…

200 篇论文

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…

计算机视觉与模式识别 · 计算机科学 2024-11-22 Zhenzhi Wang , Jingbo Wang , Yixuan Li , Dahua Lin , Bo Dai

Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention. However, existing methods face challenges such as complex interaction and limited control capabilities. To…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Xiaoda Yang , Jiayang Xu , Kaixuan Luan , Xinyu Zhan , Hongshun Qiu , Shijun Shi , Hao Li , Shuai Yang , Li Zhang , Checheng Yu , Cewu Lu , Lixin Yang

As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV generation methods achieve impressive results, they struggle with…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Weiqi Li , Shijie Zhao , Chong Mou , Xuhan Sheng , Zhenyu Zhang , Qian Wang , Junlin Li , Li Zhang , Jian Zhang

Lightweight, controllable, and physically plausible human motion synthesis is crucial for animation, virtual reality, robotics, and human-computer interaction applications. Existing methods often compromise between computational efficiency,…

计算机视觉与模式识别 · 计算机科学 2025-01-29 Arvin Tashakori , Arash Tashakori , Gongbo Yang , Z. Jane Wang , Peyman Servati

This paper introduces OmniMotion-X, a versatile multimodal framework for whole-body human motion generation, leveraging an autoregressive diffusion transformer in a unified sequence-to-sequence manner. OmniMotion-X efficiently supports…

计算机视觉与模式识别 · 计算机科学 2025-10-23 Guowei Xu , Yuxuan Bian , Ailing Zeng , Mingyi Shi , Shaoli Huang , Wen Li , Lixin Duan , Qiang Xu

We present OmniBooth, an image generation framework that enables spatial control with instance-level multi-modal customization. For all instances, the multimodal instruction can be described through text prompts or image references. Given a…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Leheng Li , Weichao Qiu , Xu Yan , Jing He , Kaiqiang Zhou , Yingjie Cai , Qing Lian , Bingbing Liu , Ying-Cong Chen

This work introduces MotionLCM, extending controllable motion generation to a real-time level. Existing methods for spatial-temporal control in text-conditioned motion generation suffer from significant runtime inefficiency. To address this…

计算机视觉与模式识别 · 计算机科学 2024-12-31 Wenxun Dai , Ling-Hao Chen , Jingbo Wang , Jinpeng Liu , Bo Dai , Yansong Tang

State-of-the-art text-to-motion generation models rely on the kinematic-aware, local-relative motion representation popularized by HumanML3D, which encodes motion relative to the pelvis and to the previous frame with built-in redundancy.…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Zichong Meng , Zeyu Han , Xiaogang Peng , Yiming Xie , Huaizu Jiang

We introduce DreamControl, a novel methodology for learning autonomous whole-body humanoid skills. DreamControl leverages the strengths of diffusion models and Reinforcement Learning (RL): our core innovation is the use of a diffusion prior…

Denoising diffusion models have shown great promise in human motion synthesis conditioned on natural language descriptions. However, integrating spatial constraints, such as pre-defined motion trajectories and obstacles, remains a challenge…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Korrawe Karunratanakul , Konpat Preechakul , Supasorn Suwajanakorn , Siyu Tang

Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within a single model. However, existing controllable generation frameworks are typically…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Liyang Li , Wen Wang , Canyu Zhao , Tianjian Feng , Zhiyue Zhao , Hao Chen , Chunhua Shen

Learning motion tracking from rich human motion data is a foundational task for achieving general control in humanoid robots, enabling them to perform diverse behaviors. However, discrepancies in morphology and dynamics between humans and…

机器人学 · 计算机科学 2026-03-02 Yuhan Li , Peiyuan Zhi , Yunshen Wang , Tengyu Liu , Sixu Yan , Wenyu Liu , Xinggang Wang , Baoxiong Jia , Siyuan Huang

Creating expressive character animations is labor-intensive, requiring intricate manual adjustment of animators across space and time. Previous works on controllable motion generation often rely on a predefined set of dense spatio-temporal…

图形学 · 计算机科学 2025-07-28 Inwoo Hwang , Jinseok Bae , Donggeun Lim , Young Min Kim

We introduce Unimotion, the first unified multi-task human motion model capable of both flexible motion control and frame-level motion understanding. While existing works control avatar motion with global text conditioning, or with…

计算机视觉与模式识别 · 计算机科学 2024-10-01 Chuqiao Li , Julian Chibane , Yannan He , Naama Pearl , Andreas Geiger , Gerard Pons-moll

End-to-end human animation, such as audio-driven talking human generation, has undergone notable advancements in the recent few years. However, existing methods still struggle to scale up as large general video generation models, limiting…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Gaojie Lin , Jianwen Jiang , Jiaqi Yang , Zerong Zheng , Chao Liang

3D human dance motion is a cooperative and elegant social movement. Unlike regular simple locomotion, it is challenging to synthesize artistic dance motions due to the irregularity, kinematic complexity and diversity. It requires the…

图形学 · 计算机科学 2020-06-11 Wenlin Zhuang , Yangang Wang , Joseph Robinson , Congyi Wang , Ming Shao , Yun Fu , Siyu Xia

Developing robust autonomous loco-manipulation skills for humanoids remains an open problem in robotics. While RL has been applied successfully to legged locomotion, applying it to complex, interaction-rich manipulation tasks is harder…

Motions in a video primarily consist of camera motion, induced by camera movement, and object motion, resulting from object movement. Accurate control of both camera and object motion is essential for video generation. However, existing…

计算机视觉与模式识别 · 计算机科学 2024-07-17 Zhouxia Wang , Ziyang Yuan , Xintao Wang , Tianshui Chen , Menghan Xia , Ping Luo , Ying Shan

Many studies decompose human motion into local motion in a frame attached to the root joint and global motion of the root joint in the world frame, treating them separately. However, these two components are not independent. Global movement…

计算机视觉与模式识别 · 计算机科学 2025-09-12 Ha Linh Nguyen , Tze Ho Elden Tse , Angela Yao

Prior approaches injecting camera control into diffusion models have focused on specific subsets of 4D consistency tasks: novel view synthesis, text-to-video with camera control, image-to-video, amongst others. Therefore, these fragmented…

计算机视觉与模式识别 · 计算机科学 2026-01-26 Xiang Fan , Sharath Girish , Vivek Ramanujan , Chaoyang Wang , Ashkan Mirzaei , Petr Sushko , Aliaksandr Siarohin , Sergey Tulyakov , Ranjay Krishna
‹ 上一页 1 2 3 10 下一页 ›