AI Paper Atlas

Research map / 3D vision / Human pose estimation

Contact-guided Real2Sim from Monocular Video with Planar Scene Primitives

Zihan Wang, Jiashun Wang, Jeff Tan, Yiwen Zhao, Jessica K. Hodgins, Shubham Tulsiani, Deva Ramanan

ICLR 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture

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
replace dense NKSR mesh with planar primitives (ablation)CRISP · overall humanoid RLsuccess rate (%): 79.3% -> 93.1%Improved
replace TSDF mesh with planar primitives (ablation)CRISP · overall humanoid RLsuccess rate (%): 75.9% -> 93.1%Improved
replace dense meshes with planar primitives (ablation)CRISP · simulation throughputFPS: 16K -> 23KImproved
use NKSR instead of planar primitives (ablation)CRISP · PROX bidirectional ChamferChamfer distance: 0.187 -> 0.163Improved
use planar primitives instead of NKSR (ablation)CRISP · PROX one-way ChamferChamfer distance: 0.187 -> 0.174Improved
use TSDF instead of planar primitives (ablation)CRISP · PROXnon-penetration: 0.947 -> 0.925Hurt
add contact-guided scene completion (ablation)CRISP · PROXbidirectional Chamfer distance: 0.193 -> 0.187Improved
add contact-guided scene completion (ablation)CRISP · PROXsuccess rate (%): 90.9% -> 90.9%No clear effect
add RL motion refinement (ablation)CRISP · EMDB HMRWA-MPJPE100 (mm): 78.16 -> 70.60Improved
add RL motion refinement (ablation)CRISP · EMDB HMRjitter: 13.04 -> 8.14Improved
add RL motion refinement (ablation)VideoMimic · EMDB HMRWA-MPJPE100 (mm): 110.64 -> 145.24Hurt
CRISP versus VideoMimicCRISP · humanoid RL overallsuccess rate (%): 44.8% -> 93.1%Improved

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