AI Paper Atlas

Research map / 3D vision / 3D generation

Online 3D Instance Segmentation at task-oriented granularity with Unposed Monocular Video

Dong Wu, Baicheng Li, Yingdian Cao, Shunkai Zhou, Yiwen Lu, Hongbin Zha

ECCV 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 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
add geometric association metric (GAM) (ablation)Ours · ReplicaAP50: 17.3 -> 23.4Improved
add semantic similarity metric (SSM) (ablation)Ours · ReplicaAP50: 21.7 -> 23.4Improved
add mutual exclusivity metric (MEM) (ablation)Ours · ReplicaAP50: 8.2 -> 23.4Improved
add MEM (ablation)Ours · ReplicaAP25: 12.0 -> 37.3Improved
add IoU-based cluster merging (ablation)Ours · ReplicaAP50: 13.8 -> 23.4Improved
add priority-ordered mask merging (descending confidence) (ablation)Ours · ReplicaAP50: 20.3 -> 23.4Improved
add priority-ordered mask merging (ablation)Ours · ReplicaAP25: 33.8 -> 37.3Improved
replace GT pose/depth with MASt3R-SLAM input for OnlineAnySegOurs · ScanNet200 val (class-agnostic)AP50: 36.1 -> 4.7Hurt
replace GT pose/depth with MASt3R-SLAM input for Open-YOLO 3DOurs · ScanNet200 val (open-vocabulary)AP50: 31.7 -> 0.8Hurt
use our online unposed method instead of offline PanSt3ROurs · ReplicaAP50: 20.9 -> 23.4Improved

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