AI Paper Atlas

Research map / Point clouds / Segmentation and detection

SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features

Jinyuan Qu, Hongyang Li, Xingyu Chen, Shilong Liu, Yukai Shi, Tianhe Ren, Ruitao Jing, Lei Zhang

AAAI 2026 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 1 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 globally enhanced 2D image-level features in the encoder (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 26.8 -> 35.2Improved
add 2D object-level queries in the decoder (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 26.8 -> 33.0Improved
combine object-level features with image-level features (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 35.2 -> 38.3Improved
add box-modulated cross-attention (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 38.3 -> 39.8Improved
use predicted boxes to filter distant masks (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 39.8 -> 40.2Improved
use 3D encoder global context fusion instead of MLP fusion (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 35.9 -> 39.8Improved
use nearest views instead of farthest views (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 36.2 -> 39.8Improved
add distance-aware attention mask in DACA-2D (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 36.3 -> 39.8Improved
use 2D object queries instead of mapping 2D features to 3D points (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 35.7 -> 39.8Improved
add 70% dropout of 2D object queries in training (ablation)SegDINO3D · ScanNet200 val (DINO-X ablation)mAP: 39.2 -> 39.8Improved
add center positional embedding without box modulation (ablation)SegDINO3D box queries · ScanNet200 val (DINO-X ablation)mAP: 38.3 -> 38.1No clear effect
add box size regression without modulation (ablation)SegDINO3D box queries · ScanNet200 val (DINO-X ablation)mAP: 38.1 -> 37.8No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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