AI Paper Atlas

Research map / Point clouds / Shape and surface completion

PU-EVA: An Edge-Vector Based Approximation Solution for Flexible-Scale Point Cloud Upsampling

Luqing Luo, Lulu Tang, Wanyi Zhou, Shizheng Wang, Zhi-Xin Yang

ICCV 2021 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 53 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 second-order error term of Taylor's expansion (ablation)PU-EVA · 4x, Sparse (256) inputCD / HD (x1e-3): CD 2.318 -> 1.784; HD 18.713 -> 13.939Improved
add second-order error term of Taylor's expansion (ablation)PU-EVA · 4x, Medium (2,048) inputCD / HD (x1e-3): CD 0.312 -> 0.266; HD 4.622 -> 3.070Improved
add second-order error term of Taylor's expansion (ablation)PU-EVA · 4x, Dense (4,096) inputCD / HD (x1e-3): CD 0.157 -> 0.123; HD 5.535 -> 1.394Improved
use EVA upsampling unit instead of feature duplication (ablation)PU-EVA · 4x, Sparse (256) inputCD / HD (x1e-3): CD 2.94 -> 1.78; HD 24.67 -> 13.93Improved
use EVA upsampling unit instead of feature duplication (ablation)PU-EVA · 4x, Medium (2,048) inputCD / HD (x1e-3): CD 0.38 -> 0.26; HD 3.99 -> 3.07Improved
use EVA upsampling unit instead of feature duplication (ablation)PU-EVA · 4x, Dense (4,096) inputCD / HD (x1e-3): CD 0.13 -> 0.12; HD 4.47 -> 1.39Improved
use EVA upsampling unit instead of NodeShuffle (ablation)PU-EVA · 4x, Sparse (256) inputCD / HD (x1e-3): CD 1.86 -> 1.78; HD 15.56 -> 13.93Improved
use EVA upsampling unit instead of NodeShuffle (ablation)PU-EVA · 4x, Medium (2,048) inputCD / HD (x1e-3): CD 0.27 -> 0.26; HD 4.66 -> 3.07Improved
use EVA upsampling unit instead of NodeShuffle (ablation)PU-EVA · 4x, Dense (4,096) inputCD / HD (x1e-3): CD 0.12 -> 0.12; HD 3.11 -> 1.39Improved
use PU-EVA instead of PU-GAN under input noisePU-EVA · Gaussian noise sigma=0.02CD / HD (x1e-3): CD 0.912 -> 0.864; HD 11.326 -> 9.178Improved
use PU-EVA instead of PU-GAN on dense inputPU-EVA · 4x, Dense (4,096) inputHD (x1e-3): HD 1.284 -> 1.394Hurt
use PU-EVA instead of PU-GAN on sparse inputPU-EVA · 4x, Sparse (256) inputHD / P2F (x1e-3): CD 2.072 -> 1.784; HD 16.592 -> 13.939; P2F 8.055 -> 8.727Mixed

Earlier methods this paper compares with

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