AI Paper Atlas

Research map / Point clouds / Shape and surface completion

I-Filtering: Implicit Filtering for Learning Neural Distance Functions From 3D Point Clouds

Shengtao Li, Yudong Liu, Ge Gao, Ming Gu, Yu-Shen Liu

TPAMI 2025 · 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
add zero level set filter (L_zero) (ablation)L_CD · FAMOUSChamfer L2 x1000: 0.031 -> 0.018Improved
add CD loss to the pull loss (ablation)L_pull · FAMOUSChamfer L2 x1000: 0.083 -> 0.031Improved
add non-zero level set filtering (L_field) (ablation)L_CD + L_zero · FAMOUSChamfer L2 x1000: 0.018 -> 0.011Improved
add L_dist term completing the full loss (ablation)L_CD + L_zero + L_field · FAMOUSChamfer L2 x1000: 0.011 -> 0.008Improved
use bidirectional projection distance instead of single direction (ablation)implicit filter · FAMOUSChamfer L2 x1000: 0.024 -> 0.008Improved
add Eikonal term (ablation)full method with CD · FAMOUSChamfer L2 x1000: 0.008 -> 0.009No clear effect
use Eikonal term without CD loss (ablation)full method · FAMOUSChamfer L2 x1000: 0.008 -> 0.021Hurt
set CD weight alpha_3 to 10 instead of 0 (ablation)full method · FAMOUSChamfer L2 x1000: 0.013 -> 0.008Improved
raise CD weight alpha_3 from 10 to 100 (ablation)full method · FAMOUSChamfer L2 x1000: 0.008 -> 0.009Hurt
increase sigma_n from 15 to 30 degrees (ablation)implicit filter · FAMOUSChamfer L2 x1000: 0.008 -> 0.011Hurt
use diagonal instead of max for sigma_p (ablation)implicit filter · FAMOUSChamfer L2 x1000: 0.008 -> 0.011Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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