AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds

Junsheng Zhou, Baorui Ma, Yu-Shen Liu, Yi Fang, Zhizhong Han

NeurIPS 2022 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 5 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
replace the two-stage progressive loss with the Neural-Pull loss (ablation)Ours · ShapeNet Car subsetL2CD: 0.1112 -> 0.2381Hurt
replace |x| with 1-exp(-x) at the last layer (ablation)Ours · ShapeNet Car subsetL2CD: 0.1112 -> 0.1218Hurt
train second stage from scratch instead of end-to-end (ablation)Ours · ShapeNet Car subsetL2CD: 0.1112 -> 0.1497Hurt
increase training stages from 1 to 2 (ablation)Ours · ShapeNet Car subsetL2CD: 0.1218 -> 0.1112Improved
increase training stages from 2 to 3 or 4 (ablation)Ours · ShapeNet Car subsetL2CD: 0.1112 -> 0.1107No clear effect
low confidence range 0.9 sigma instead of 1.1 sigma (ablation)Ours · ShapeNet Car subsetL2CD: 0.1112 -> 0.1133Hurt
low confidence range 1.2 sigma instead of 1.1 sigma (ablation)Ours · ShapeNet Car subsetL2CD: 0.1112 -> 0.1131Hurt
add mesh refinement using UDF values at 64^3 grid (ablation)Ours · ShapeNet Car subsetL2CD: 0.4169 -> 0.1606Improved
add mesh refinement at 256^3 grid (ablation)Ours · ShapeNet Car subsetL2CD: 0.1294 -> 0.1112Improved
increase grid resolution from 64^3 to 320^3 (ablation)Ours · ShapeNet Car subsetL2CD and time: 0.1606 -> 0.1105; 3.0 s -> 307.6 sMixed
apply our gradient-based reconstruction to NDF instead of BPANDF · ShapeNet carsChamfer-L2 mean: 0.202 -> 0.160Improved
use our UDF method instead of NDFNDF · MGDChamfer-L2: 0.658 -> 0.117Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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