AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projections Matching

Chao Chen, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker

ICCV 2021 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 2 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 second directional distance term to a first-term-only loss (ablation)2D projection matching loss · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 24.47 -> 4.16Improved
add the first directional distance term to a second-term-only loss (ablation)2D projection matching loss · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 8.49 -> 4.16Improved
use 5 nearest neighbors in first term (ablation)2D projection matching loss · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.16 -> 4.25No clear effect
use 5 nearest neighbors in second term (ablation)2D projection matching loss · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.16 -> 4.32No clear effect
use 5 nearest neighbors in both terms (ablation)2D projection matching loss · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.16 -> 4.29No clear effect
increase irregular supervision points from 1000 to 5000 (ablation)2D projection matching · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.29 -> 4.16Improved
increase irregular supervision points beyond 5000 to 9000 (ablation)2D projection matching · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.16 -> 4.19No clear effect
use structure adaptive sampling instead of Poisson-disk sampling (ablation)2D projection matching · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.35 -> 4.16Improved
use structure adaptive sampling instead of random sampling (ablation)2D projection matching · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.23 -> 4.16Improved
use structure adaptive sampling instead of pixel sampling (ablation)2D projection matching · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.20 -> 4.16Improved
use structure adaptive sampling instead of dynamic random sampling (ablation)2D projection matching · ShapeNet Chair (32^2 images, 2000 points)Chamfer distance x100: 4.36 -> 4.16Improved
replace per-pixel difference supervision (DRWR) with 2D projection matchingpoint cloud generation · ShapeNet Chair 16000 points, 128^2 to 32^2 imagesCD degradation x100: 0.46 -> 0.31Improved

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