AI Paper Atlas

Research map / Point clouds / Shape and surface completion

SeedFormer: Patch Seeds Based Point Cloud Completion with Upsample Transformer

Haoran Zhou, Yun Cao, Wenqing Chu, Junwei Zhu, Tong Lu, Ying Tai, Chengjie Wang

ECCV 2022 · Point clouds › Shape and surface completion · approach: Structure-guided completion · 222 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 Patch Seeds representation instead of global feature (ablation)SeedFormer · PCN datasetCD-Avg: 6.97 -> 6.74Improved
use 256 seeds instead of 128 (ablation)SeedFormer · PCN datasetCD-Avg: 7.00 -> 6.74Improved
use 512 seeds instead of 256 (ablation)SeedFormer · PCN datasetCD-Avg: 6.74 -> 6.75No clear effect
use Upsample Transformer instead of folding generator (ablation)SeedFormer · PCN datasetCD-Avg: 6.93 -> 6.74Improved
use Upsample Transformer instead of deconvolution generator (ablation)SeedFormer · PCN datasetCD-Avg: 6.90 -> 6.74Improved
use Upsample Transformer instead of graph convolution (ablation)SeedFormer · PCN datasetCD-Avg: 6.88 -> 6.74Improved
use Upsample Transformer instead of point-wise attention (ablation)SeedFormer · PCN datasetCD-Avg: 6.85 -> 6.74Improved
remove softmax in seed generator self-attention (ablation)SeedFormer · PCN datasetCD-Avg: 6.83 -> 6.74Improved
use scaled-softmax instead of no softmax (ablation)SeedFormer · PCN datasetCD-Avg: 6.74 -> 6.80Hurt
add positional encoding (ablation)Upsample Transformer · PCN datasetCD-Avg: 6.88 -> 6.80Improved
add regional encoding from seed features to positional encoding (ablation)Upsample Transformer · PCN datasetCD-Avg: 6.80 -> 6.74Improved
combine positional and regional into one joint encoding (ablation)Upsample Transformer · PCN datasetCD-Avg: 6.74 -> 6.78Hurt

Later papers that compared with this method

18 later accepted papers report SeedFormer as a baseline in their results tables; 18 of them report a better number on most of the results they share with it.

10 more not listed.

Earlier methods this paper compares with

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