AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

STaR: Self-Supervised Tracking and Reconstruction of Rigid Objects in Motion With Neural Rendering

Wentao Yuan, Zhaoyang Lv, Tanner Schmidt, Steven Lovegrove

CVPR 2021 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 65 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 appearance initialization (ablation)STaR · Lamp and deskPSNR: 20.78 -> 32.95Improved
add appearance initialization (ablation)STaR · Lamp and deskSSIM: 0.820 -> 0.957Improved
add appearance initialization (ablation)STaR · Lamp and deskLPIPS: 0.188 -> 0.023Improved
use online training instead of training over the entire video (ablation)STaR · Lamp and deskPSNR: 25.98 -> 32.95Improved
use online training instead of training over the entire video (ablation)STaR · Lamp and deskSSIM: 0.925 -> 0.957Improved
use online training instead of training over the entire video (ablation)STaR · Lamp and deskLPIPS: 0.079 -> 0.023Improved
add entropy regularization (ablation)STaR · Lamp and deskPSNR: 32.88 -> 32.95Improved
add entropy regularization (ablation)STaR · Lamp and deskSSIM: 0.959 -> 0.957Hurt
add entropy regularization (ablation)STaR · Lamp and deskLPIPS: 0.032 -> 0.023Improved

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