AI Paper Atlas

Research map / Point clouds / Segmentation and detection

All in One: Visual-Description-Guided Unified Point Cloud Segmentation

Zongyan Han, Mohamed El Amine Boudjoghra, Jiahua Dong, Jinhong Wang, Rao Muhammad Anwer

ICCV 2025 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 3 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 LLM description queries, image queries, SVC loss and spatial enhancement to OneFormer3DOneFormer3D · S3DIS Area-5PQ: 62.2 -> 66.3Improved
add Spatial Enhancement Module (ablation)VDG-Uni3DSeg · S3DIS Area-5mAP: 58.1 -> 60.1Improved
add description queries (ablation)VDG-Uni3DSeg · S3DIS Area-5mIoU: 70.2 -> 71.5Improved
add image queries (ablation)VDG-Uni3DSeg · S3DIS Area-5mIoU: 70.4 -> 71.5Improved
add Semantic-Visual Contrastive loss (ablation)VDG-Uni3DSeg · S3DIS Area-5PQ: 62.2 -> 66.3Improved
use CLIP-selected top-5 internet images instead of random images (ablation)VDG-Uni3DSeg · S3DIS Area-5PQ: 62.0 -> 66.3Improved
increase sparse-attention sample size from 16 to 128 (ablation)Spatial Enhancement Module · ScanNet validationPQ: 70.1 -> 71.5Improved
apply VDG-Uni3DSeg instead of OneFormer3D on ScanNet hidden testOneFormer3D · ScanNet hidden testmAP25: 89.6 -> 88.0Hurt
apply VDG-Uni3DSeg instead of OneFormer3D on ScanNet200OneFormer3D · ScanNet200 validationmAP50: 40.0 -> 40.0No clear effect
apply VDG-Uni3DSeg instead of OneFormer3D on S3DIS 6-foldOneFormer3D · S3DIS 6-fold cross-validationmIoU: 72.8 -> 73.2No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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