中文
相关论文

相关论文: What about gravity in video generation? Post-Train…

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

Text-to-video generative models have made significant strides in recent years, producing high-quality videos that excel in both aesthetic appeal and accurate instruction following, and have become central to digital art creation and user…

机器学习 · 计算机科学 2025-05-02 Xuyang Guo , Jiayan Huo , Zhenmei Shi , Zhao Song , Jiahao Zhang , Jiale Zhao

Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process of post-training these models for accurate world modeling…

计算机视觉与模式识别 · 计算机科学 2025-03-13 Chenyu Li , Oscar Michel , Xichen Pan , Sainan Liu , Mike Roberts , Saining Xie

Generating realistic human motion is a central yet unsolved challenge in video generation. While reinforcement learning (RL)-based post-training has driven recent gains in general video quality, extending it to human motion remains…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Yidong Huang , Zun Wang , Han Lin , Dong-Ki Kim , Shayegan Omidshafiei , Jaehong Yoon , Jaemin Cho , Yue Zhang , Mohit Bansal

Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of…

计算机视觉与模式识别 · 计算机科学 2026-01-19 Qiyuan Zhang , Biao Gong , Shuai Tan , Zheng Zhang , Yujun Shen , Xing Zhu , Yuyuan Li , Kelu Yao , Chunhua Shen , Changqing Zou

Video generators are increasingly evaluated as potential world models, which requires them to encode and understand physical laws. We investigate their representation of a fundamental law: gravity. Out-of-the-box video generators…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Varun Varma Thozhiyoor , Shivam Tripathi , Venkatesh Babu Radhakrishnan , Anand Bhattad

Recent advances in video diffusion models have remarkably improved camera-controlled video generation, but most methods rely solely on supervised fine-tuning (SFT), leaving online reinforcement learning (RL) post-training largely…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Zhaoqing Wang , Xiaobo Xia , Zhuolin Bie , Jinlin Liu , Dongdong Yu , Jia-Wang Bian , Changhu Wang

Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We identify a specification bottleneck: text prompts are lossy…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Yuxiang Feng , Juncheng Wang , Chao Xu , Yijie Qian , Huihan Wang , Wenlong Hou , Yang Liu , Baigui Sun , Yong Liu , Shujun Wang

Recent advances in image and video generation raise hopes that these models possess world modeling capabilities, the ability to generate realistic, physically plausible videos. This could revolutionize applications in robotics, autonomous…

The ultimate goal of video generation is to satisfy a fundamental trilemma: achieving high visual quality, maintaining rigorous physical consistency, and enabling precise controllability. While recent models can maintain this balance in…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Tianshuo Xu , Zhifei Chen , Leyi Wu , Hao Lu , Ying-cong Chen

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human…

Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Juyi Lin , Arash Akbari , Yumei He , Lin Zhao , Haichao Zhang , Arman Akbari , Xingchen Xu , Zoe Y. Lu , Enfu Nan , Hokin Deng , Edmund Yeh , Sarah Ostadabbas , Yun Fu , Jennifer Dy , Pu Zhao , Yanzhi Wang

Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Jan Ackermann , Shengqu Cai , Boyang Deng , Zhengfei Kuang , Songyou Peng , Gordon Wetzstein

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a…

计算机视觉与模式识别 · 计算机科学 2026-05-01 Sriram Narayanan , Ziyu Jiang , Srinivasa Narasimhan , Manmohan Chandraker

Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel framework for…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Chen Wang , Chuhao Chen , Yiming Huang , Zhiyang Dou , Yuan Liu , Jiatao Gu , Lingjie Liu

A current limitation of video generative video models is that they generate plausible looking frames, but poor motion -- an issue that is not well captured by FVD and other popular methods for evaluating generated videos. Here we go beyond…

Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical cognition have gradually received widespread attention -…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Minghui Lin , Xiang Wang , Yishan Wang , Shu Wang , Fengqi Dai , Pengxiang Ding , Cunxiang Wang , Zhengrong Zuo , Nong Sang , Siteng Huang , Donglin Wang

Human motion synthesis is an important problem with applications in graphics, gaming and simulation environments for robotics. Existing methods require accurate motion capture data for training, which is costly to obtain. Instead, we…

计算机视觉与模式识别 · 计算机科学 2022-08-15 Kevin Xie , Tingwu Wang , Umar Iqbal , Yunrong Guo , Sanja Fidler , Florian Shkurti

Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Tinghui Zhu , Sheng Zhang , James Y. Huang , Selena Song , Xiaofei Wen , Yuankai Li , Hoifung Poon , Muhao Chen

Can we learn the physics of matter in motion directly from images and video--and trust it? Answering this question requires integrating experiments, physics-based simulation, and data across traditionally separate disciplines. Much of this…

计算工程、金融与科学 · 计算机科学 2026-04-21 Hagen Holthusen , Kevin Linka , Ellen Kuhl
‹ 上一页 1 2 3 10 下一页 ›