AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection

Junsheng Zhou, Baorui Ma, Shujuan Li, Yu-Shen Liu, Zhizhong Han

ICCV 2023 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 46 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 the three zero level set constraints (projection, distance, orthogonal) (ablation)LevelSetUDF · ShapeNet Cars subsetL2 Chamfer (x10^4): 0.126 -> 0.091Improved
add level set projection loss (ablation)LevelSetUDF · ShapeNet Cars subsetL2 Chamfer (x10^4): 0.107 -> 0.091Improved
add surface unsigned distance loss (ablation)LevelSetUDF · ShapeNet Cars subsetL2 Chamfer (x10^4): 0.101 -> 0.091Improved
add gradient-surface orthogonal loss (ablation)LevelSetUDF · ShapeNet Cars subsetL2 Chamfer (x10^4): 0.096 -> 0.091Improved
add adaptive per-point weights (ablation)LevelSetUDF · ShapeNet Cars subsetNormal Consistency: 84.2 -> 84.4Improved
use projection loss on the zero level set instead of GenSDF-style optimization (ablation)LevelSetUDF · ShapeNet Cars subsetL2 Chamfer (x10^4): 0.101 -> 0.091Improved
apply projection loss on the zero level set rather than a random non-zero level set (ablation)LevelSetUDF · ShapeNet Cars subsetL2 Chamfer (x10^4): 0.098 -> 0.091Improved
increase projection loss weight from 0.002 to 0.1 (ablation)LevelSetUDF · ShapeNet Cars subsetL2 Chamfer (x10^4): 0.091 -> 0.359Hurt
increase orthogonal loss weight from 0.01 to 1 (ablation)LevelSetUDF · ShapeNet Cars subsetL2 Chamfer (x10^4): 0.091 -> 2.55Hurt
add zero level set constraints for unsupervised normal estimation (ablation)LevelSetUDF · PCPNet (average)angle RMSE: 7.61 -> 7.20Improved
add zero level set constraints for point cloud upsampling (ablation)LevelSetUDF · PU-GANHD: 2.16 -> 1.55Improved
vary adaptive weight lambda from 10 to 1000 (ablation)LevelSetUDF · ShapeNet Cars subsetNormal Consistency: 84.4 -> 83.2Hurt

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