AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Human Pose Estimation via Intuitive Physics

Shashank Tripathi, Lea Müller, Chun-Hao P. Huang, Omid Taheri, Michael J. Black, Dimitrios Tzionas

CVPR 2023 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 96 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add ground and stability losses to HMRHMR* · RICHMPJPE: 82.5 -> 79.0Improved
Add ground and stability losses to HMRHMR* · RICHBOS error (%): 62.0 -> 71.2Improved
Add stability loss alone (ablation)HMR* · RICHPAMPJPE: 48.3 -> 47.5Improved
Add ground loss alone (ablation)HMR* · RICHMPJPE: 82.5 -> 80.9Improved
Add intuitive-physics lossesHMR* · Human3.6MMPJPE: 61.6 -> 60.6Improved
Add ground and stability lossesSMPLify-XMC · MoYoMPJPE: 75.3 -> 71.9Improved
Add stability loss alone (ablation)SMPLify-XMC · MoYoMPJPE: 75.3 -> 88.5Hurt
Add ground loss alone (ablation)SMPLify-XMC · MoYoMPJPE: 75.3 -> 73.3Improved
Add push loss only (ablation)HMR* · RICHMPJPE: 82.5 -> 85.4Hurt
Add pull loss only (ablation)HMR* · RICHMPJPE: 82.5 -> 88.0Hurt
Use push and pull losses together instead of either alone (ablation)HMR* · RICHMPJPE: 85.4 -> 80.9; 88.0 -> 80.9Improved
Use volume-weighted part-specific mass for COM rather than naive vertex mean (ablation)SMPL body COM estimation · MoYoCOM error (mm): 264.1 mm -> 53.3 mmImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy