Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
Kiana Ehsani, Shubham Tulsiani, Saurabh Gupta, Ali Farhadi, Abhinav Gupta
2020Year
22Top-tier citations
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 9c715f0f-4dd7-4191-9876-3a3a6621b87dCited by top-tier papers22
- Hand-Object Contact Consistency Reasoning for Human Grasps GenerationHanwen Jiang, Shaowei Liu, Jiashun Wang, Xiaolong WangICCV 2021 · 242 citations
- BEHAVE: Dataset and Method for Tracking Human Object InteractionsBharat Lal Bhatnagar, Xianghui Xie, Ilya A. Petrov, Cristian Sminchisescu et al.CVPR 2022 · 144 citations
- gradSim: Differentiable simulation for system identification and visuomotor controlJ. Krishna Murthy, Miles Macklin, Florian Golemo, Vikram Voleti et al.ICLR 2021 · 130 citations
- Residual Force Control for Agile Human Behavior Imitation and Extended Motion SynthesisYe Yuan, Kris KitaniNeurIPS 2020 · 105 citations
- D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object InteractionsSammy Joe Christen, Muhammed Kocabas, Emre Aksan, Jemin Hwangbo et al.CVPR 2022 · 69 citations
Related papers
- Seeing the Wind from a Falling LeafZhiyuan Gao, Jiageng Mao, Hong-Xing Yu, Haozhe Lou et al.NeurIPS 2025 · 10 citations
- 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 et al.SIGGRAPH 2024 · 2 citations
- CARI4D: Category Agnostic 4D Reconstruction of Human-Object InteractionXianghui Xie, Bowen Wen, Yan Chang, Hesam Rabeti et al.CVPR 2026 · 16 citations
