Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
Kiana Ehsani, Shubham Tulsiani, Saurabh Gupta, Ali Farhadi, Abhinav Gupta
2020年份
22顶会引用
摘要
Input Videos Output Contact points + Forces Simulated Result Applying Forces Figure 1: We study the problem of physical understanding of human-object interactions by inferring object motion, points of contacts and forces from RGB videos. We use physics simulation to see how these interactions change the dynamics of the object and try to imitate the motion observed in the video.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper22
- Hand-Object Contact Consistency Reasoning for Human Grasps GenerationHanwen Jiang, Shaowei Liu, Jiashun Wang, Xiaolong WangICCV 2021 · 被引用 242 次
- BEHAVE: Dataset and Method for Tracking Human Object InteractionsBharat Lal Bhatnagar, Xianghui Xie, Ilya A. Petrov, Cristian Sminchisescu 等CVPR 2022 · 被引用 144 次
- gradSim: Differentiable simulation for system identification and visuomotor controlJ. Krishna Murthy, Miles Macklin, Florian Golemo, Vikram Voleti 等ICLR 2021 · 被引用 130 次
- Residual Force Control for Agile Human Behavior Imitation and Extended Motion SynthesisYe Yuan, Kris KitaniNeurIPS 2020 · 被引用 105 次
- D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object InteractionsSammy Joe Christen, Muhammed Kocabas, Emre Aksan, Jemin Hwangbo 等CVPR 2022 · 被引用 69 次
相关 Paper
- Seeing the Wind from a Falling LeafZhiyuan Gao, Jiageng Mao, Hong-Xing Yu, Haozhe Lou 等NeurIPS 2025 · 被引用 10 次
- Recovering Physically Plausible Human-Object Interactions from Monocular VideosDingbang Huang, Etienne Vouga, Qixing Huang, Georgios PavlakosCVPR 2026
- Object pop-up: Can we infer 3D objects and their poses from human interactions alone?Ilya A. Petrov, Riccardo Marin, Julian Chibane, Gerard Pons-MollCVPR 2023
- Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with PhysicsHaoyu Hu, Xinyu Yi, Zhe Cao, Jun-Hai Yong 等SIGGRAPH 2024 · 被引用 2 次
- CARI4D: Category Agnostic 4D Reconstruction of Human-Object InteractionXianghui Xie, Bowen Wen, Yan Chang, Hesam Rabeti 等CVPR 2026 · 被引用 16 次
