AI Paper Atlas

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

Zoo3D: Zero-Shot 3D Object Detection at Scene Level

Andrey Lemeshko, Bulat Gabdullin, Nikita Drozdov, Anton Konushin, Danila Rukhovich, Maksim Kolodiazhnyi

CVPR 2026 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 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
train class-agnostic TR3D detector on pseudo labels (Zoo3D_1 vs Zoo3D_0)Zoo3D · Point cloud + posed images, ScanNet20mAP25: 34.7 -> 37.2Improved
second iteration of pseudo-label retraining (Zoo3D_2) (ablation)Zoo3D_1 · Class-agnostic ScanNet200, posed imagesmAP25: 36.1 -> 37.6Improved
first iteration of self-training (ablation)Zoo3D_0 · Class-agnostic ScanNet200, posed imagesmAP25: 22.4 -> 36.1Improved
add occlusion filter to open-vocabulary module (ablation)Zoo3D_0 · Open-vocabulary module ablation, posed images ScanNet200mAP25: 14.7 -> 14.8No clear effect
add SAM mask refinement (ablation)Zoo3D_0 · Open-vocabulary module ablation, posed images ScanNet200mAP25: 14.8 -> 15.4Improved
add multi-scale processing (ablation)Zoo3D_0 · Open-vocabulary module ablation, posed images ScanNet200mAP50: 5.7 -> 6.3Improved
add multi-scale processing (ablation)Zoo3D_0 · Open-vocabulary module ablation, posed images ScanNet200mAP25: 15.4 -> 16.5Improved
increase number of images per scene from 15 to 45 (ablation)Zoo3D_0 · Posed images ScanNet200, number of viewsmAP25: 9.6 -> 14.3Improved
use DUSt3R instead of DROID-SLAM for reconstruction (ablation)Zoo3D_1 · Unposed images ScanNet200 class-agnosticmAP25: 2.4 -> 19.0Improved
use VGGT instead of DUSt3R for reconstruction (ablation)Zoo3D_1 · Unposed images ScanNet200 class-agnosticmAP25: 19.0 -> 28.2Improved
assign all objects to 16-cm level instead of 32-cm level (ablation)Zoo3D_1 class-agnostic detector · Posed images ScanNet200 class-agnosticmAP25: 31.2 -> 36.1Improved
assign objects 50/50 by size instead of all to 16-cm level (ablation)Zoo3D_1 class-agnostic detector · Posed images ScanNet200 class-agnosticmAP25: 36.1 -> 34.5Hurt

Later papers that compared with this method

1 later accepted paper reports Zoo3D_1 as a baseline in their results tables; 1 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 2 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