中文
相关论文

相关论文: Rebalancing Reference Frame Dominance to Improve M…

200 篇论文

We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Previous text-to-motion methods focus on characters in isolation without considering scenes due to the limited availability of…

计算机视觉与模式识别 · 计算机科学 2024-04-17 Hongwei Yi , Justus Thies , Michael J. Black , Xue Bin Peng , Davis Rempe

We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Alexander Pondaven , Aliaksandr Siarohin , Sergey Tulyakov , Philip Torr , Fabio Pizzati

We present DuoMo, a generative method that recovers human motion in world-space coordinates from unconstrained videos with noisy or incomplete observations. Reconstructing such motion requires solving a fundamental trade-off: generalizing…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Yufu Wang , Evonne Ng , Soyong Shin , Rawal Khirodkar , Yuan Dong , Zhaoen Su , Jinhyung Park , Kris Kitani , Alexander Richard , Fabian Prada , Michael Zollhofer

Diffusion models have recently gained significant attention in robotics due to their ability to generate multi-modal distributions of system states and behaviors. However, a key challenge remains: ensuring precise control over the generated…

机器人学 · 计算机科学 2025-10-01 Luobin Wang , Hongzhan Yu , Chenning Yu , Sicun Gao , Henrik Christensen

Slow motion videos are becoming increasingly popular, but capturing high-resolution videos at extremely high frame rates requires professional high-speed cameras. To mitigate this problem, current techniques increase the frame rate of…

计算机视觉与模式识别 · 计算机科学 2020-04-22 Avinash Paliwal , Nima Khademi Kalantari

Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Wonjoon Jin , Jiyun Won , Janghyeok Han , Qi Dai , Chong Luo , Seung-Hwan Baek , Sunghyun Cho

Videos provide a rich source of information, but it is generally hard to extract dynamical parameters of interest. Inferring those parameters from a video stream would be beneficial for physical reasoning. Robots performing tasks in dynamic…

机器人学 · 计算机科学 2020-08-31 Martin Asenov , Michael Burke , Daniel Angelov , Todor Davchev , Kartic Subr , Subramanian Ramamoorthy

Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…

计算机视觉与模式识别 · 计算机科学 2025-05-01 Zihan Zhou , Changrui Dai , Aibo Song , Xiaolin Fang

Recent advancements in text-to-video (T2V) diffusion models have significantly enhanced the visual quality of the generated videos. However, even recent T2V models find it challenging to follow text descriptions accurately, especially when…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Jialu Li , Shoubin Yu , Han Lin , Jaemin Cho , Jaehong Yoon , Mohit Bansal

Recent high-performing image-to-video (I2V) models based on variants of the diffusion transformer (DiT) have displayed remarkable inherent world-modeling capabilities by virtue of training on large scale video datasets. We investigate…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Aaron Appelle , Jerome P. Lynch

Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tuning large-scale video models for specific tasks, which becomes…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Sangwon Jang , Taekyung Ki , Jaehyeong Jo , Jaehong Yoon , Soo Ye Kim , Zhe Lin , Sung Ju Hwang

Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Jian Yang , Dacheng Yin , Yizhou Zhou , Fengyun Rao , Wei Zhai , Yang Cao , Zheng-Jun Zha

Text-to-motion generation is a formidable task, aiming to produce human motions that align with the input text while also adhering to human capabilities and physical laws. While there have been advancements in diffusion models, their…

计算机视觉与模式识别 · 计算机科学 2023-08-31 Hanyang Kong , Kehong Gong , Dongze Lian , Michael Bi Mi , Xinchao Wang

Recent advances in text-to-video (T2V) generation with diffusion models have garnered significant attention. However, they typically perform well in scenes with a single object and motion, struggling in compositional scenarios with multiple…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Yuanhang Li , Qi Mao , Lan Chen , Zhen Fang , Lei Tian , Xinyan Xiao , Libiao Jin , Hua Wu

Repurposing pre-trained diffusion models has been proven to be effective for NVS. However, these methods are mostly limited to a single object; directly applying such methods to compositional multi-object scenarios yields inferior results,…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Ruijie Lu , Yixin Chen , Junfeng Ni , Baoxiong Jia , Yu Liu , Diwen Wan , Gang Zeng , Siyuan Huang

Recent advancements in video generation, particularly in diffusion models, have driven notable progress in text-to-video (T2V) and image-to-video (I2V) synthesis. However, challenges remain in effectively integrating dynamic motion signals…

计算机视觉与模式识别 · 计算机科学 2025-07-04 Ziye Li , Hao Luo , Xincheng Shuai , Henghui Ding

Text-to-image diffusion model alignment is critical for improving the alignment between the generated images and human preferences. While training-based methods are constrained by high computational costs and dataset requirements,…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Xin Xie , Dong Gong

Training an effective video action recognition model poses significant computational challenges, particularly under limited resource budgets. Current methods primarily aim to either reduce model size or utilize pre-trained models, limiting…

计算机视觉与模式识别 · 计算机科学 2023-07-28 Harry Cheng , Yangyang Guo , Liqiang Nie , Zhiyong Cheng , Mohan Kankanhalli

Diffusion-based \textit{image-to-video} (I2V) generation has become a central direction in generative models by turning a reference image, with optional conditions, into a temporally coherent video. Compared with broader video generation…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Xianlong Wang , Wenbo Pan , Shijia Zhou , Ke Li , Yuqi Wang , Zeyu Ye , Hangtao Zhang , Leo Yu Zhang , Xiaohua Jia

Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex motions that natural…

计算机视觉与模式识别 · 计算机科学 2025-10-23 Aritra Bhowmik , Denis Korzhenkov , Cees G. M. Snoek , Amirhossein Habibian , Mohsen Ghafoorian