AI Paper Atlas

Research map / 3D vision / Face and shape

Phase Transitions, Distance Functions, and Implicit Neural Representations

Yaron Lipman

ICML 2021 · 3D vision › Face and shape · approach: Implicit neural representation design · 1 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 PHASE instead of the strongest listed baselinesurface reconstruction benchmark with point clouds and normals · Anchor, Daratech, DC, Gargoyle, and Lord Quasd_C: Anchor: 0.22 -> 0.21; Daratech: 0.20 -> 0.18; DC: 0.14 -> 0.15; Gargoyle: 0.16 -> 0.16; Lord Quas: 0.12 -> 0.11Mixed
use PHASE instead of the strongest listed baselinesurface reconstruction benchmark with point clouds and normals · Anchor, Daratech, DC, Gargoyle, and Lord Quasd_H: Anchor: 4.49 -> 4.29; Daratech: 3.14 -> 2.92; DC: 1.35 -> 2.52; Gargoyle: 3.20 -> 3.14; Lord Quas: 0.69 -> 0.96Mixed
add Fourier features to PHASE and train on points onlyPHASE · Anchor, Daratech, DC, Gargoyle, Lord Quasd_C: Anchor: 0.72 -> 0.29; Daratech: 2.48 -> 0.35; DC: 0.86 -> 0.19; Gargoyle: 0.26 -> 0.17; Lord Quas: 0.49 -> 0.11Improved
add the unit-gradient loss at input points (ablation)PHASE · 2D point-cloud reconstructionssurface regularity at data pointsImproved
decrease epsilon (ablation)PHASE · 2D point-cloud reconstructionsdistance-function approximationImproved
add Fourier features to PHASE (ablation)PHASE with normal data · surface reconstruction benchmarkd_C: Anchor: 0.21 -> 0.24; Daratech: 0.18 -> 0.18; DC: 0.15 -> 0.15; Gargoyle: 0.16 -> 0.16; Lord Quas: 0.11 -> 0.12Mixed
remove the gradient loss (mu=0 instead of mu=0.1) (ablation)PHASE · 2D point-cloud reconstructionssurface regularity at data pointsHurt
use Fourier features with IGR rather than PHASEimplicit surface reconstruction from point clouds · surface reconstruction benchmark, points onlyextraneous surface partsHurt

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