AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap

Yongwei Chen, Zihao Wang, Longkun Zou, Ke Chen, Kui Jia

ECCV 2022 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 12 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
train on stereo-rendered SpeckleNet10 instead of ModelNet10DGCNN · DepthScanNet10accuracy: 46.7 -> 64.0Improved
train on SpeckleNet10 instead of ModelNet10PointNet++ · DepthScanNet10accuracy: 48.4 -> 60.9Improved
train on SpeckleNet10 instead of ModelNet10RSCNN · DepthScanNet10accuracy: 49.7 -> 53.9Improved
train on SpeckleNet10 instead of ModelNet10SimpleView · DepthScanNet10accuracy: 54.6 -> 62.3Improved
use DepthScanNet-like noise via stereo matching instead of clean depth (add stereo rendering and matching noise) (ablation)DGCNN · S->Daccuracy: 53.2 -> 64.0Improved
use Mesh2Point instead of Blensor simulation (ablation)DGCNN · S->Daccuracy: 56.6 -> 64.0Improved
use Mesh2Point instead of ModelNet10 with random region dropout (ablation)DGCNN · S->Daccuracy: 50.4 -> 64.0Improved
use Mesh2Point instead of Blensor (ablation)SimpleView · S->Daccuracy: 65.1 -> 62.3Hurt
use Mesh2Point instead of ModelNet10-Dropout (ablation)RSCNN · S->Daccuracy: 56.5 -> 53.9Hurt
add PCM mixup augmentationDGCNN · M->Daccuracy: 46.7 -> 61.2Improved
add QBST on top of PCM instead of SPSTDGCNN+PCM · S->Daccuracy: 71.9 -> 72.4Improved
use QBST instead of CBST on top of PCMDGCNN+PCM · S->Daccuracy: 62.9 -> 72.4Improved

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