AI Paper Atlas

Research map / Point clouds / Shape and surface completion

PU-GAN: A Point Cloud Upsampling Adversarial Network

Ruihui Li, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng

ICCV 2019 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 546 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 discriminator (GAN framework) (ablation)PU-GAN · Ablation test setCD (1e-3): 0.57 -> 0.28Improved
add the discriminator (GAN framework) (ablation)PU-GAN · Ablation test setuniformity p=0.4% (1e-3): 7.02 -> 3.38Improved
add uniform loss (ablation)PU-GAN · Ablation test setCD (1e-3): 0.51 -> 0.28Improved
add uniform loss (ablation)PU-GAN · Ablation test setP2F (1e-3): 3.99 -> 2.33Improved
add self-attention unit (ablation)PU-GAN · Ablation test setCD (1e-3): 0.46 -> 0.28Improved
add self-attention unit (ablation)PU-GAN · Ablation test setHD (1e-3): 6.01 -> 4.64Improved
add up-down-up expansion unit (ablation)PU-GAN · Ablation test setCD (1e-3): 0.35 -> 0.28Improved
add up-down-up expansion unit (ablation)PU-GAN · Ablation test setP2F (1e-3): 3.02 -> 2.33Improved
add farthest sampling (ablation)PU-GAN · Ablation test setCD (1e-3): 0.31 -> 0.28Improved
add farthest sampling (ablation)PU-GAN · Ablation test setHD (1e-3): 4.96 -> 4.64Improved
use full PU-GAN instead of basic GAN baseline (ablation)GAN baseline · Ablation test setCD (1e-3): 0.59 -> 0.28Improved
upsample inputs with PU-GAN before classificationPointNet · ModelNet40classification accuracy (%): 82.4% -> 83.8%Improved

Later papers that compared with this method

7 later accepted papers report PU-GAN as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

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