AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Voxel-Based Network for Shape Completion by Leveraging Edge Generation

Xiaogang Wang, Marcelo H Ang, Gim Hee Lee

ICCV 2021 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 86 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 multi-scale grid transformation (vs binary voxelization) (ablation)VE-PCN without EG · Own dataset ablation (2048 points)CD x1e-4: 5.792 -> 3.600Improved
use MGT instead of differentiable Gridding (ablation)VE-PCN without EG · Own dataset ablation (2048 points)CD x1e-4: 4.768 -> 3.600Improved
add edge generator (ablation)VE-PCN · Own dataset ablation (2048 points)CD x1e-4: 3.600 -> 2.669Improved
use generated complete edges instead of calculated partial edges (ablation)VE-PCN · Own dataset ablation (2048 points)CD x1e-4: 3.586 -> 2.669Improved
use partial edges instead of no edges (ablation)VE-PCN without EG · Own dataset ablation (2048 points)CD x1e-4: 3.600 -> 3.586No clear effect
add edge generation (ablation)VE-PCN · KITTI carsfidelity distance: 0.0279 -> 0.0258Improved
add Chamfer distance loss (ablation)VE-PCN · Own dataset loss ablation (2048 points)CD x1e-4: 3.408 -> 2.669Improved
add sharper Chamfer distance loss (ablation)VE-PCN · Own dataset loss ablation (2048 points)CD x1e-4: 2.886 -> 2.669Improved
add density loss (ablation)VE-PCN · Own dataset loss ablation (2048 points)CD x1e-4: 2.843 -> 2.669Improved
add BCE loss (ablation)VE-PCN · Own dataset loss ablation (2048 points)CD x1e-4: 2.842 -> 2.669Improved
increase output resolution from 2048 to 16384 pointsVE-PCN · Own dataset (seen)CD x1e-4: 2.669 -> 1.620Improved
test on unseen categories vs GRNetVE-PCN · Own dataset unseenCD x1e-4: 3.892 -> 3.176Improved

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