AI Paper Atlas

Research map / Point clouds / Shape and surface completion

SPoVT: Semantic-Prototype Variational Transformer for Dense Point Cloud Semantic Completion

Sheng Yu Huang, Hao-Yu Hsu, Yu-Chiang Frank Wang

NeurIPS 2022 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 0 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 reconstruction pretrain to baseline model (ablation)SPoVT · PCN ChairmIoU: 43.07 -> 62.83Improved
add reconstruction pretrain to baseline model (ablation)SPoVT · PCN ChairChamfer Distance: 5.23 -> 5.01Improved
add ratio predictor theta_P (ablation)SPoVT · PCN ChairmIoU: 62.83 -> 81.33Improved
add ratio predictor theta_P (ablation)SPoVT · PCN ChairChamfer Distance: 5.01 -> 4.40Improved
add Semantic VAE (ablation)SPoVT · PCN ChairChamfer Distance: 4.40 -> 2.99Improved
add Semantic VAE (ablation)SPoVT · PCN ChairmIoU: 81.33 -> 84.81Improved
add L_GCD loss (ablation)SPoVT · PCN ChairChamfer Distance: 2.99 -> 2.36Improved
add L_GCD loss (ablation)SPoVT · PCN ChairmIoU: 84.81 -> 85.22Improved
use segmentation labels predicted by pre-trained DGCNN instead of ground truth (ablation)SPoVT · PCN averageChamfer Distance: 2.51 -> 2.85Hurt
use segmentation labels predicted by pre-trained DGCNN instead of ground truth (ablation)SPoVT · PCN averagemIoU: 85.7 -> 81.2Hurt
train one unified model on Airplane and Car (ablation)SPoVT · PCN AirplaneChamfer Distance: 0.73 -> 0.84Hurt
train one unified model on Airplane and Car (ablation)SPoVT · PCN CarChamfer Distance: 2.86 -> 3.39Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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