AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Geodesic-Former: A Geodesic-Guided Few-Shot 3D Point Cloud Instance Segmenter

Tuan Ngo, Khoi Nguyen

ECCV 2022 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 6 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
replace cosine similarity with a similarity network (ablation)DyCo3D baseline · ScanNetV2 val (1-shot)mAP: 6.2 -> 6.6Improved
replace clustering with transformer decoder (ablation)DyCo3D baseline · ScanNetV2 val (1-shot)mAP: 6.2 -> 6.7Improved
add geodesic distance embedding to dynamic convolution (ablation)DyCo3D baseline · ScanNetV2 val (1-shot)mAP: 6.2 -> 7.8Improved
add geodesic embedding to transformer decoder variant (ablation)Transformer decoder · ScanNetV2 val (1-shot)mAP: 6.7 -> 9.4Improved
add similarity network to transformer decoder + geodesic embedding (ablation)Geodesic-Former · ScanNetV2 val (1-shot)mAP: 9.4 -> 10.6Improved
add similarity network to transformer decoder + geodesic embedding (ablation)Geodesic-Former · ScanNetV2 val (1-shot)AP50: 17.1 -> 19.8Improved
use classification head instead of similarity network (ablation)Geodesic-Former · ScanNetV2 val (1-shot)mAP: 10.6 -> 4.5Hurt
use per-point classification baseline instead of DyCo3D clustering (ablation)DyCo3D baseline · ScanNetV2 val (1-shot)mAP: 6.2 -> 4.9Hurt
use 2 dynamic conv layers instead of 1 (ablation)Geodesic-Former · ScanNetV2 test setmAP: 3.4 -> 10.6Improved
use 4 dynamic conv layers instead of 2 (ablation)Geodesic-Former · ScanNetV2 test setmAP: 10.6 -> 6.4Hurt
ball query kappa=64 instead of 16 (tau 0.05 m) (ablation)Geodesic-Former · ScanNetV2 valmAP: 9.2 -> 10.6Improved
increase kappa from 64 to 128 (tau 0.05 m) (ablation)Geodesic-Former · ScanNetV2 valmAP: 10.6 -> 10.6No clear effect

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