AI Paper Atlas

Research map / Point clouds / Shape and surface completion

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

Aihua Mao, Zihui Du, Yu-Hui Wen, Jun Xuan, Yong-Jin Liu

ECCV 2022 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 57 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 8 flow blocks instead of 4 (ablation)PD-Flow · PUSet 10K 2%CD: 3.55 -> 3.25Improved
use 12 flow blocks instead of 8 (ablation)PD-Flow · PUSet 10K 2%CD: 3.25 -> 3.57No clear effect
use inverse pass of the flow instead of MLP point generator (ablation)PD-Flow · PUSet 10K 2%CD: 4.65 -> 3.25Improved
use inverse pass of the flow instead of MLP point generator (ablation)PD-Flow · PUSet 10K 2%P2M: 2.14 -> 1.03Improved
add dimension augmentation channels (D_a from 0) (ablation)PD-Flow · training convergenceloss curveImproved
use LCC filter instead of FBM (ablation)PD-Flow · PUSet 10K 2%CD: 3.40 -> 3.26Improved
use LBM filter instead of LCC (ablation)PD-Flow · PUSet 10K 2%CD: 3.26 -> 3.50Hurt
add L_LCC loss (ablation)PD-Flow with LCC · PUSet 10K 2%CD: 3.48 -> 3.26Improved
add L_LBM loss (ablation)PD-Flow with LBM · PUSet 10K 2%CD: 3.65 -> 3.50Improved
mask at least 32 channels (D_m >= 32) with D_a = 32 (ablation)PD-Flow FBM · training curveconvergenceHurt
use PD-Flow instead of ScoreDenoise on 10K 3% noiseScore · PUSet 10K 3%CD: 4.69 -> 4.45Improved
use PD-Flow instead of ScoreDenoise on 50K 3% noiseScore · PUSet 50K 3%CD: 1.92 -> 1.94No 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