AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations

Peng-Hao Hsu, Ke Zhang, Fu-En Wang, Tao Tu, Ming-Feng Li, Yu-Lun Liu, Albert Y. C. Chen, Min Sun, Cheng-Hao Kuo

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 5 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
use graph-embedding pseudo boxes instead of OV-3DET boxes for training (ablation)OpenM3D · ScanNet200 class-agnosticAP@25 (%): 19.53 -> 26.92Improved
use graph-embedding pseudo boxes instead of SAM3D boxes for training (ablation)OpenM3D · ScanNet200 OV detectionmAP@25 (%): 3.92 -> 4.23Improved
add mesh segmentation refinement to pseudo boxes (ablation)OpenM3D · ScanNet200 class-agnosticAP@25 (%): 25.95 -> 26.92Improved
use CropFormer instead of SAM for 2D segments (ablation)OpenM3D · ScanNet200 OV detectionmAP@25 (%): 4.23 -> 4.76 mAP; 15.12 -> 14.62 mARMixed
use single-stage voxel-semantic alignment instead of two-stage CLIP classification (S2D) (ablation)OpenM3D · ScanNet200 OV detectionmAR@25 (%): 10.05 -> 15.12Improved
use single-stage OpenM3D instead of S2D (ablation)OpenM3D · ScanNet200 OV detectionmAP@25 (%): 4.17 -> 4.23No clear effect
use single-stage OpenM3D instead of S2D (ablation)OpenM3D · ARKitScenesmAR@25: 19.58 -> 42.77Improved
swap CLIP ViT-L/14 for ViT-B/16 or ViT-B/32 in alignment (ablation)OpenM3D · ScanNet200 OV detectionmAP@25 (%): 4.23 -> 4.16 (B/16), 4.02 (B/32)No clear effect
use CIFAR100 prompts instead of ImageNet prompts (ablation)OpenM3D · ScanNet200 OV detectionmAP@25 (%): 4.23 -> 4.14No clear effect
use graph embedding clustering of 2D segments instead of SAM3D sequential merging (ablation)3D pseudo box generation · ScanNet200 pseudo boxesprecision@25 (%): 14.48 -> 32.07Improved
pseudo boxes vs SAM3D on recall@50 (ablation)3D pseudo box generation · ScanNet200 pseudo boxesrecall@50 (%): 36.07 -> 32.99Hurt
use estimated depth with multi-view depth estimator instead of OpenM3DS2D baseline · ScanNet200 inference timeseconds per scene: 0.3 -> 81Hurt

Later papers that compared with this method

2 later accepted papers report OpenM3D as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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