AI Paper Atlas

Research map / 3D vision / 3D generation

Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects

Atsuhiro Noguchi, Umar Iqbal, Jonathan Tremblay, Tatsuya Harada, Orazio Gallo

CVPR 2022 · 3D vision › 3D generation · approach: Hand-object interaction generation · 34 citations (OpenAlex)

Check 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 the part-merging loss (ablation)Watch It Move · ZJU-MoCap subject 366Joint MPJPE (mm): 8.49 -> 10.25Hurt
Add the structure-discovery loss L_Gamma (ablation)Watch It Move · ZJU-MoCap subject 366Joint MPJPE (mm): 9.35 -> 8.49Improved
Add ellipsoid surface regularization L_E (ablation)Watch It Move · ZJU-MoCap subject 366Joint MPJPE (mm): 12.13 -> 8.49Improved
Add part coverage loss L_t (ablation)Watch It Move · ZJU-MoCap subject 366Novel view LPIPS: 0.063 -> 0.061Mixed
Add the separation loss (ablation)Watch It Move · ZJU-MoCap subject 366Joint MPJPE (mm): 9.72 -> 8.49Improved
Predict an SDF residual Δd instead of the full SDF (ablation)Watch It Move · ZJU-MoCap subject 366Joint MPJPE (mm): 22.14 -> 8.49Improved

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