AI Paper Atlas

Research map / Point clouds / Point cloud classification

Progressive Seed Generation Auto-Encoder for Unsupervised Point Cloud Learning

Juyoung Yang, Pyunghwan Ahn, Doyeon Kim, Haeil Lee, Junmo Kim

ICCV 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 25 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
replace random uniform seed with fixed grid seed (ablation)FoldingNet-style decoder · ShapeNetCorev2 (decoder ablation, PointNet encoder)chamfer distance x10^4: 7.96 -> 7.43Improved
generate 2D seed from codeword instead of random seed (ablation)FoldingNet-style decoder · ShapeNetCorev2 (decoder ablation, PointNet encoder)chamfer distance x10^4: 7.96 -> 7.34Improved
generate 2D seed from codeword instead of fixed grid (ablation)FoldingNet-style decoder · ShapeNetCorev2 (decoder ablation, PointNet encoder)chamfer distance x10^4: 7.43 -> 7.34Improved
expand generated seed from 2D points to 32-dimensional features (ablation)Decoder C2 · ShapeNetCorev2 (decoder ablation, PointNet encoder)chamfer distance x10^4: 7.34 -> 6.84Improved
add seed feature propagation modules (1 to 3) progressively (ablation)Decoder C32 · ShapeNetCorev2 (decoder ablation, PointNet encoder)chamfer distance x10^4: 6.84 -> 6.38Improved
add a third SFPM after two (ablation)Decoder C32 + 2 SFPMs · ShapeNetCorev2 (decoder ablation, PointNet encoder)chamfer distance x10^4: 6.40 -> 6.38No clear effect
use 1024-dim codeword instead of 512-dim (ablation)PSG-Net · ShapeNetCorev2 reconstructionchamfer distance x10^4: 5.78 -> 5.15Improved
add seed generation module to AtlasNet with 32 patchesAtlasNet · ShapeNetCorev2 reconstructionchamfer distance x10^4: 5.66 -> 5.31Improved
combine PSG-Net decoder with PointGLRPointGLR · ModelNet40 unsupervised classificationaccuracy (%): 92.22 -> 92.59Improved
use single-patch PSG-Net instead of multi-patch AtlasNetAtlasNet-125 · ShapeNetCorev2 reconstructionchamfer distance x10^4: 5.66 -> 5.78No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 4 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