中文
相关论文

相关论文: MotiMotion: Motion-Controlled Video Generation wit…

200 篇论文

A primary bottleneck in large-scale text-to-video generation today is physical consistency and controllability. Despite recent advances, state-of-the-art models often produce unrealistic motions, such as objects falling upward, or abrupt…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Yu Yuan , Xijun Wang , Tharindu Wickremasinghe , Zeeshan Nadir , Bole Ma , Stanley H. Chan

We address goal-based imitation learning, where the aim is to output the symbolic goal from a third-person video demonstration. This enables the robot to plan for execution and reproduce the same goal in a completely different environment.…

机器人学 · 计算机科学 2019-11-15 De-An Huang , Yu-Wei Chao , Chris Paxton , Xinke Deng , Li Fei-Fei , Juan Carlos Niebles , Animesh Garg , Dieter Fox

Recent motion-language models unify tasks like comprehension and generation but operate at a coarse granularity, lacking fine-grained understanding and nuanced control over body parts needed for animation or interaction. This stems from…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Bizhu Wu , Jinheng Xie , Wenting Chen , Zhe Kong , Jianfeng Ren , Linlin Shen , Ruibin Bai , Rong Qu

Recent advancements in video generation models have significantly improved their ability to follow text prompts. However, the customization of dynamic visual effects, defined as temporally evolving and appearance-driven visual phenomena…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Rui Zhao , Mike Zheng Shou

Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts. However, extending these techniques to video generation remains challenging, with existing text-to-video…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Weifeng Chen , Yatai Ji , Jie Wu , Hefeng Wu , Pan Xie , Jiashi Li , Xin Xia , Xuefeng Xiao , Liang Lin

Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to support fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Li-Heng Chen , Ke Cheng , Yahui Liu , Lei Shi , Shi-Sheng Huang , Hongbo Fu

Current video generation models produce physically inconsistent motion that violates real-world dynamics. We propose TrajVLM-Gen, a two-stage framework for physics-aware image-to-video generation. First, we employ a Vision Language Model to…

计算机视觉与模式识别 · 计算机科学 2025-10-02 Fan Yang , Zhiyang Chen , Yousong Zhu , Xin Li , Jinqiao Wang

Human-human motion generation is essential for understanding humans as social beings. Current methods fall into two main categories: single-person-based methods and separate modeling-based methods. To delve into this field, we abstract the…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Yabiao Wang , Shuo Wang , Jiangning Zhang , Ke Fan , Jiafu Wu , Zhucun Xue , Yong Liu

We present CoMoGen, a controllable video generation framework that generates realistic interactive dynamics from a single binary mask sequence conditioned on an input image. CoMoGen introduces a lightweight MaskAdapter that encodes binary…

计算机视觉与模式识别 · 计算机科学 2026-05-25 Adil Meric , Lin Geng Foo , Mert Kiray , Benjamin Busam , Rishabh Dabral , Christian Theobalt

Customized text-to-video generation aims to generate text-guided videos with user-given subjects, which has gained increasing attention. However, existing works are primarily limited to single-subject oriented text-to-video generation,…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Hong Chen , Xin Wang , Guanning Zeng , Yipeng Zhang , Yuwei Zhou , Feilin Han , Yaofei Wu , Wenwu Zhu

Video Generation is a relatively new and yet popular subject in machine learning due to its vast variety of potential applications and its numerous challenges. Current methods in Video Generation provide the user with little or no control…

计算机视觉与模式识别 · 计算机科学 2021-11-22 Bahman Rouhani , Mohammad Rahmati

Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements, typically involving labor-intensive real-world capturing. Despite advancements in generative AI for video…

计算机视觉与模式识别 · 计算机科学 2024-06-24 Yaowei Li , Xintao Wang , Zhaoyang Zhang , Zhouxia Wang , Ziyang Yuan , Liangbin Xie , Yuexian Zou , Ying Shan

Text-to-motion generation has recently garnered significant research interest, primarily focusing on generating human motion sequences in blank backgrounds. However, human motions commonly occur within diverse 3D scenes, which has prompted…

计算机视觉与模式识别 · 计算机科学 2025-05-06 Ziyan Guo , Haoxuan Qu , Hossein Rahmani , Dewen Soh , Ping Hu , Qiuhong Ke , Jun Liu

While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods for single-motion customization have been developed to…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Youcan Xu , Zhen Wang , Jiaxin Shi , Kexin Li , Feifei Shao , Jun Xiao , Yi Yang , Jun Yu , Long Chen

Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses rigidly bind motion to the driving viewpoint, precluding…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Zhixue Fang , Xu He , Songlin Tang , Haoxian Zhang , Qingfeng Li , Xiaoqiang Liu , Pengfei Wan , Kun Gai

Human motion generation aims to generate natural human pose sequences and shows immense potential for real-world applications. Substantial progress has been made recently in motion data collection technologies and generation methods, laying…

计算机视觉与模式识别 · 计算机科学 2023-11-16 Wentao Zhu , Xiaoxuan Ma , Dongwoo Ro , Hai Ci , Jinlu Zhang , Jiaxin Shi , Feng Gao , Qi Tian , Yizhou Wang

While text-to-video diffusion models have made significant strides, many still face challenges in generating videos with temporal consistency. Within diffusion frameworks, guidance techniques have proven effective in enhancing output…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Hyelin Nam , Jaemin Kim , Dohun Lee , Jong Chul Ye

Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Nate Gillman , Yinghua Zhou , Zitian Tang , Evan Luo , Arjan Chakravarthy , Daksh Aggarwal , Michael Freeman , Charles Herrmann , Chen Sun

We propose a unified framework for motion control in video generation that seamlessly integrates camera movement, object-level translation, and fine-grained local motion using trajectory-based inputs. In contrast to prior methods that…

计算机视觉与模式识别 · 计算机科学 2025-06-11 Angtian Wang , Haibin Huang , Jacob Zhiyuan Fang , Yiding Yang , Chongyang Ma

Video generation has advanced rapidly, improving evaluation methods, yet assessing video's motion remains a major challenge. Specifically, there are two key issues: 1) current motion metrics do not fully align with human perceptions; 2) the…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Xinran Ling , Chen Zhu , Meiqi Wu , Hangyu Li , Xiaokun Feng , Cundian Yang , Aiming Hao , Jiashu Zhu , Jiahong Wu , Xiangxiang Chu