AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Parametric Surface Constrained Upsampler Network for Point Cloud

Pingping Cai, Zhenyao Wu, Xinyi Wu, Song Wang

AAAI 2023 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 10 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 the parametric surface constrained upsampler instead of PU-GCNPoint cloud upsampling · PU1KCD (× 10^-4): 1.151 -> 0.886Improved
Use the parametric surface constrained upsampler instead of PU-GCNPoint cloud upsampling · PU1KP2F (× 10^-3): 2.504 -> 1.091Improved
Use the parametric surface constrained upsampler instead of PU-GCNPoint cloud upsampling · PU1KUniformity (× 10^-3), 0.4%, 0.6%, 0.8%, 1.0%: 1.95 -> 1.40; 3.97 -> 2.85; 6.83 -> 5.06; 10.63 -> 7.95Improved
Use the parametric surface constrained upsampler instead of SnowFlakePoint cloud completion · ShapeNet-PCNL1-CD (× 10^-3): 7.19 -> 7.04Improved
Use the parametric surface constrained upsampler instead of SnowFlakePoint cloud completion · ShapeNet-PCNEMD (× 10^-3): 69.13 -> 66.57Hurt
Add spatial feature aggregation with a point transformer over nearest neighbors (ablation)Parametric Surface Constrained Upsampler · PU1KCD (× 10^-4): 1.293 -> 0.886Improved
Use explicit parametric surface functions instead of an MLP folding layer (ablation)Parametric Surface Constrained Upsampler · PU1KCD (× 10^-4): 0.967 -> 0.886Improved
Add displacement loss to select a better projection plane (ablation)Parametric Surface Constrained Upsampler · PU1KCD (× 10^-4): 0.893 -> 0.886Improved
Add Gaussian perturbation to input pointsParametric Surface Constrained Upsampler · PU1KCD (× 10^-4): 0.886 -> 1.053 -> 1.280 -> 1.599Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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