AI Paper Atlas

Research map / Point clouds / Point cloud classification

DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding

Jincen Jiang, Qianyu Zhou, Yuhang Li, Xuequan Lu, Meili Wang, Lizhuang Ma, Jian Chang, Jian Jun Zhang

ECCV 2024 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 8 citations (OpenAlex)

Read the paper

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 anchor/prototype with global and local prototype-based anchor selection (ablation)DG-PIC · ScanObjectNN targetChamfer Distance (reconstruction): 8.4 -> 6.8Improved
use both global and local prototypes instead of only one level (ablation)DG-PIC · ScanObjectNN targetChamfer Distance (denoising): 38.3 / 36.7 -> 35.1Improved
shift target toward all source domains instead of one nearest domain (uniform averaging) (ablation)DG-PIC · ScanObjectNN targetChamfer Distance (reconstruction): 6.8 -> 6.3; registration 6.2 -> 6.5No clear effect
add macro-level similarity-weighted shifting (ablation)DG-PIC · ScanObjectNN targetChamfer Distance (denoising): 32.4 -> 22.7Improved
add micro-level patch-position shifting (ablation)DG-PIC · ScanObjectNN targetChamfer Distance (denoising): 32.4 -> 25.6Improved
combine macro and micro-level feature shifting (ablation)DG-PIC · ScanObjectNN targetChamfer Distance (denoising): 22.7 -> 15.2Improved
train-time domain generalization mixing (Pointmixup, PointCutMix) in multi-domain multi-task settingtask-specific models · ScanObjectNN targetChamfer Distance: PointCutMix recon 44.8 vs PointNet 41.1No clear effect
add test-time dual-level feature shifting and multi-domain prompt pairing to PICPIC · ScanObjectNN targetChamfer Distance (reconstruction): 72.9 -> 4.1Improved

Later papers that compared with this method

1 later accepted paper reports DG-PIC as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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