AI Paper Atlas

Research map / Point clouds / Segmentation and detection

SegPoint: Segment Any Point Cloud via Large Language Model

Shuting He, Henghui Ding, Xudong Jiang, Bihan Wen

ECCV 2024 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 35 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 Geometric Enhancer Module (KPConv-based local geometry injected via gated cross-attention) (ablation)SegPoint vanilla baseline · Instruct3D valmIoU: 16.1 -> 21.4Improved
add Geometric Enhancer Module (ablation)SegPoint vanilla baseline · ScanRefermIoU: 30.3 -> 35.8Improved
add Geometric-guided Feature Propagation (ablation)SegPoint vanilla baseline · Instruct3D valmIoU: 16.1 -> 23.2Improved
add Geometric-guided Feature Propagation (ablation)SegPoint vanilla baseline · ScanRefermIoU: 30.3 -> 38.1Improved
combine GEM and GFP (ablation)SegPoint · Instruct3D valmIoU: 23.2 -> 27.5Improved
use GEM instead of full fine-tuning of point encoder (ablation)SegPoint · Instruct3D valmIoU: 26.2 -> 27.5Improved
use GEM instead of LoRA adaptation (ablation)SegPoint · Instruct3D valmIoU: 24.8 -> 27.5Improved
use LLM-based unified model versus two-stage and single-stage specialist methodsSegPoint · Instruct3D valmIoU: 12.8 -> 27.5Improved
unified LLM model compared with specialist semantic segmentation methodsSegPoint · ScanNet valmIoU: 75.7 -> 74.1No clear effect

Later papers that compared with this method

2 later accepted papers report SegPoint as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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