AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds

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

ECCV 2024 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 12 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 zero level set filter loss L_zero to L_CD (ablation)Implicit Filtering · FAMOUSCD_L2 x1000: 0.031 -> 0.018Improved
add non-zero level set filtering L_field (ablation)Implicit Filtering · FAMOUSCD_L2 x1000: 0.018 -> 0.011Improved
add L_dist term (ablation)Implicit Filtering · FAMOUSCD_L2 x1000: 0.011 -> 0.008Improved
use bidirectional projection distance instead of single-direction (ablation)Implicit Filtering · FAMOUSF-score: 0.726 -> 0.778Improved
use Chamfer distance loss instead of pull loss (ablation)Implicit Filtering · FAMOUSCD_L2 x1000: 0.083 -> 0.031Improved
add Eikonal term alongside CD loss (ablation)Implicit Filtering · FAMOUSCD_L2 x1000: 0.008 -> 0.009 (CD_L2 without vs with Eikonal)No clear effect
use Eikonal term instead of CD loss for gradient constraint (ablation)Implicit Filtering · FAMOUSCD_L2 x1000: 0.008 -> 0.021Hurt
increase CD loss weight alpha3 from 10 to 100 (ablation)Implicit Filtering · FAMOUSF-score: 0.778 -> 0.774Hurt
set alpha3 to 0 (drop CD constraint) (ablation)Implicit Filtering · FAMOUSF-score: 0.778 -> 0.758Hurt
widen sigma_n from 15 to 30/45/60 degrees (ablation)Implicit Filtering · FAMOUSF-score: 0.778 -> 0.771 / 0.764 / 0.767Hurt
set sigma_p to bounding box diagonal rather than max neighbor distance (ablation)Implicit Filtering · FAMOUSF-score: 0.778 -> 0.763Hurt
apply implicit filtering for scenesImplicit Filtering vs PCP · 3D Scenenormal consistency: Lounge 0.934 (PCP) vs 0.926 (Ours)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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