Lune

Abstract

Figure 1 . Estimating a 3D body from an image is ill-posed. A recent, representative, optimization method [59] produces bodies that are in unstable poses, penetrate the floor, or hover above it. In contrast, IPMAN estimates a 3D body that is physically plausible. To achieve this, IPMAN uses novel intuitive-physics (IP) terms that exploit inferred pressure heatmaps on the body, the Center of Pressure (CoP), and the body's Center of Mass (CoM). Body heatmap colors encode per-vertex pressure.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

47 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
  • Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation cites PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
  • Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
  • Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation cites PARE: Part Attention Regressor for 3D Human Body Estimation
  • HuMoR: 3D Human Motion Model for Robust Pose Estimation cites Resolving 3D Human Pose Ambiguities With 3D Scene Constraints
  • HuMoR: 3D Human Motion Model for Robust Pose Estimation cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
  • HuMoR: 3D Human Motion Model for Robust Pose Estimation cites PARE: Part Attention Regressor for 3D Human Body Estimation
  • PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
  • PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos cites HuMoR: 3D Human Motion Model for Robust Pose Estimation
  • PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos cites PARE: Part Attention Regressor for 3D Human Body Estimation
  • PARE: Part Attention Regressor for 3D Human Body Estimation cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers47

  1. KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic SkillsWeiji Xie, Jinrui Han, Jiakun Zheng, Huanyu Li et al.NeurIPS 2025 · 120 citations
  2. Neural Localizer Fields for Continuous 3D Human Pose and Shape EstimationIstván Sárándi, Gerard Pons-MollNeurIPS 2024 · 76 citations
  3. From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent GuidanceZhe Li, Yangyang Wei, Boan Zhu, Yibo Peng et al.ICLR 2026 · 29 citations
  4. Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial SensorsYu Zhang, Songpengcheng Xia, Lei Chu, Jiarui Yang et al.CVPR 2024 · 23 citations
  5. PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular VideosYufei Zhang, Jeffrey O. Kephart, Zijun Cui, Qiang JiCVPR 2024 · 14 citations

Builds on41

  1. Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the LoopNikos Kolotouros, Georgios Pavlakos, Michael J. Black, Kostas DaniilidisICCV 2019 · 1,139 citations
  2. PARE: Part Attention Regressor for 3D Human Body EstimationMuhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, Michael J. BlackICCV 2021 · 509 citations
  3. HuMoR: 3D Human Motion Model for Robust Pose EstimationDavis Rempe, Tolga Birdal, Aaron Hertzmann, Jimei Yang et al.ICCV 2021 · 398 citations
  4. Resolving 3D Human Pose Ambiguities With 3D Scene ConstraintsMohamed Hassan, Vasileios Choutas, Dimitrios Tzionas, Michael J. BlackICCV 2019 · 384 citations
  5. PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback LoopHongwen Zhang, Yating Tian, Xinchi Zhou, Wanli Ouyang et al.ICCV 2021 · 376 citations

Related papers

  1. Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular VideoErik Gärtner, Mykhaylo Andriluka, Hongyi Xu, Cristian SminchisescuCVPR 2022 · 31 citations
  2. MotionPRO: Exploring the Role of Pressure in Human MoCap and BeyondShenghao Ren, Yi Lu, Jiayi Huang, Jiayi Zhao et al.CVPR 2025
  3. iPose: Interactive Human Pose Reconstruction from VideoJingyuan Liu, Li-Yi Wei, Ariel Shamir, Takeo IgarashiCHI 2024 · 8 citations
  4. Differentiable Dynamics for Articulated 3d Human Motion ReconstructionErik Gärtner, Mykhaylo Andriluka, Erwin Coumans, Cristian SminchisescuCVPR 2022 · 33 citations
  5. Improving Global Motion Estimation in Sparse IMU-based Motion Capture with PhysicsXinyu Yi, Shaohua Pan, Feng XuSIGGRAPH 2025 · 7 citations
Dusk over the sea between two cliffs drawn in fine vertical lines