AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Progressive Point Cloud Deconvolution Generation Network

Le Hui, Rui Xu, Jin Xie, Jianjun Qian, Jian Yang

ECCV 2020 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 70 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
use learning-based bilateral interpolation instead of reshape (ablation)PDGN · ShapeNet ChairJSD: 8.69 -> 1.71Improved
use learning-based bilateral interpolation instead of bilinear interpolation (ablation)PDGN · ShapeNet ChairJSD: 5.02 -> 1.71Improved
use bilateral instead of bilinear interpolation (ablation)PDGN · ShapeNet Chair1-NNA-CD: 69.23 -> 52.38Improved
use shape-preserving loss instead of plain adversarial loss (ablation)PDGN · ShapeNet ChairJSD: 3.28 -> 1.71Improved
use shape-preserving loss instead of EMD loss between resolutions (ablation)PDGN · ShapeNet ChairJSD: 3.35 -> 1.71Improved
use shape-preserving loss instead of CD loss between resolutions (ablation)PDGN · ShapeNet ChairJSD: 3.34 -> 1.71Improved
generate 2048 points progressively instead of stopping at 256 points (ablation)PDGN · ShapeNet ChairJSD: 5.57 -> 1.71Improved
generate 2048 points instead of 1024 points (ablation)PDGN · ShapeNet ChairJSD: 2.18 -> 1.71Improved
generate 1024 points instead of 512 points (ablation)PDGN · ShapeNet ChairMMD-EMD: 9.67 -> 11.0Hurt
set k around 20 in the neighborhood (ablation)PDGN · ShapeNet Chairgeneration metricsImproved
use PDGN instead of PointFlowPDGN vs PointFlow · ShapeNet AirplaneCOV-CD: 46.91 -> 64.98Improved
use PDGN instead of PointFlow on CarPDGN vs PointFlow · ShapeNet CarMMD-CD: 0.91 -> 1.07No clear effect

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