AI Paper Atlas

Research map / 3D vision / Face and shape

Deep Non-Rigid Structure From Motion With Missing Data

Chen Kong, Simon Lucey

TPAMI 2020 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 12 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
use 4-by-2 block sparse model to solve translation explicitlyDeep NRSfM · CMU MoCap subject 23normalized mean 3D error: 0.054 -> 0.060No clear effect
replace soft-thresholding with ReLU (ablation)Deep NRSfM · appendix comparisonnormalized mean 3D errorNo clear effect
add hierarchical layers beyond single-layer sparse codingDeep NRSfM · IKEA Averagenormalized mean 3D error: 0.117 -> 0.010Improved
handle missing points via masked first layer instead of matrix completionDeep NRSfM · PASCAL3D+ aeroplane orthogonal missingnormalized mean 3D error: 0.533 -> 0.033Improved
increase missing points up to 7 of 31 (ablation)Deep NRSfM · CMU MoCap subject 23normalized mean 3D error: 0.604Hurt
add up to 20% Gaussian noise to 2D coordinates (ablation)Deep NRSfM · CMU MoCap subject 70normalized mean 3D errorHurt
add random scale and translation (weak perspective)Deep NRSfM · PASCAL3D+ aeroplane complete no noisenormalized mean 3D error: 0.013 -> 0.034Hurt

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