AI Paper Atlas

Research map / 3D vision / Face and shape

Unsupervised 3D Reconstruction Networks

Geonho Cha, Minsik Lee, Songhwai Oh

ICCV 2019 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 17 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 low-rank prior loss (ablation)3D-URN · PASCAL3D+normalized mean 3D error e1_3D: 0.175 -> 0.168Improved
add weight regularization loss (ablation)3D-URN · PASCAL3D+normalized mean 3D error e1_3D: 0.174 -> 0.168Improved
add intermediate losses on every module (ablation)3D-URN · PASCAL3D+normalized mean 3D error e1_3D: 0.268 -> 0.168Improved
increase number of 3D reconstructors from 2 to 12 (ablation)3D-URN · PASCAL3D+normalized mean 3D error e1_3D: 0.257 -> 0.168Improved
increase reconstructors from 3 to 9 (ablation)3D-URN · PASCAL3D+normalized mean 3D error e1_3D: 0.211 -> 0.211No clear effect
use nuclear norm rather than determinant cost for low-rank loss (ablation)3D-URN · PASCAL3D+normalized mean 3D error e1_3D: +0.009 error with determinantImproved
use nuclear norm rather than log-determinant cost for low-rank loss (ablation)3D-URN · PASCAL3D+training stability: log-determinant failsImproved
add noise to 2D points (0.01 dmax)3D-URN · PASCAL3D+normalized mean 3D error e1_3D: 0.168 -> 0.177Hurt
double the noise std3D-URN · PASCAL3D+normalized mean 3D error e1_3D: 0.177 -> 0.189Hurt
evaluate on unseen instances (80/20 split)3D-URN · PASCAL3D+normalized mean 3D error e1_3D: 0.168 -> 0.166No clear effect
apply to non-rigid face sequence versus NRSfM methods3D-URN · Face sequencee2_3D: 0.023 (BMM) vs 0.044Hurt

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