AI Paper Atlas

Research map / Point clouds / Segmentation and detection

G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation

Hojun Song, Chae-yeong Song, Jeong-hun Hong, chaewon moon, Soo Ye Kim, Yiyi Liao, Jaehyup Lee, Sang-hyo Park

ECCV 2026 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 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
transfer Gaussian attributes to points (G2P) over PT v3Point Transformer V3 · ScanNet v2 valmIoU: 77.0 -> 78.4Improved
G2P vs BFANet on hidden testsegmentation · ScanNet200 hidden testmIoU: 36.0 -> 35.7No clear effect
G2P on appearance-challenging classesPoint Transformer V3 · ScanNet v2 appearance-challengingavg IoU: 66.8 -> 69.2Improved
G2P instance segmentation vs PT v3Point Transformer V3 · ScanNet200 instance valmAP: 23.1 -> 23.2No clear effect
add boundary guidance only (ablation)G2P · ScanNet v2 valmIoU: 77.0 -> 77.8Improved
add appearance distillation only (ablation)G2P · ScanNet v2 valmIoU: 77.0 -> 77.8Improved
combine boundary guidance and distillation (ablation)G2P · ScanNet v2 valmIoU: 77.8 -> 78.4Improved
use Mahalanobis distance with k=20 instead of Euclidean (ablation)G2P · ScanNet v2 valmIoU: 77.0 -> 78.4Improved
semantic-only boundary supervision (ablation)G2P · ScanNet v2 valmIoU: 77.0 -> 76.9No clear effect
add scale-based boundary pruning to semantic boundary (ablation)G2P · ScanNet v2 valmIoU: 76.9 -> 77.8Improved
increase distillation weight lambda_d (ablation)G2P · ScanNet v2 geometry-dependent classesavg IoU: 82.41 -> 80.58Mixed
use GS opacity and color inputs in distillation instead of normals (ablation)appearance encoder · ScanNet v2 valmIoU: 76.5 -> 77.8Improved

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