M:3L Lab

CVPR 2026

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

The first training-free 3D object detection framework. It constructs 3D bounding boxes through graph clustering of 2D instance masks and assigns open-vocabulary semantic labels.

Publication record

Status
Accepted at CVPR 2026
Authors
Andrey Lemeshko, Bulat Gabdullin, Nikita Drozdov, Anton Konushin, Danila Rukhovich, Maksim Kolodiazhnyi
Venue
CVPR 2026
Research area
3D Intelligence
First arXiv submission

Abstract / summary

Zoo3D introduces scene-level zero-shot 3D object detection. Its training-free Zoo3D0 mode constructs class-agnostic 3D boxes from 2D instance masks and assigns open-vocabulary labels; Zoo3D1 then trains a class-agnostic detector on Zoo3D0-generated pseudo-labels.

Methodology

  • 2D instance-mask extraction across scene views
  • Graph clustering for class-agnostic 3D bounding-box construction
  • Best-view selection and view-consensus mask generation
  • Open-vocabulary visual-language semantic labeling
  • Zero-shot Zoo3D0 and pseudo-label-based self-supervised Zoo3D1 modes
  • DUSt3R-based support for posed and unposed image inputs

Datasets and benchmarks

  • ScanNet20
  • ScanNet60
  • ScanNet200
  • ARKitScenes

Principal results

  • The paper reports state-of-the-art open-vocabulary 3D-detection results across ScanNet-based benchmarks at publication time.
  • On ScanNet200 with point-cloud inputs, Zoo3D0 reports [email protected]/[email protected] of 21.1/14.1 without training, while Zoo3D1 reports 23.5/15.2.
  • On ARKitScenes, the paper evaluates point-cloud and unposed-image tracks and reports mAP at IoU thresholds of 0.25 and 0.5.

Benchmark evidence

BenchmarkTaskInputMetricResultEvidence
ScanNet200Open-vocabulary 3D object detection (Zoo3D0)Point cloud and posed scene images; training-free[email protected] / [email protected]21.1 / 14.1Zoo3D paper, Table 2
ScanNet200Open-vocabulary 3D object detection (Zoo3D1)Point cloud and posed scene images; self-supervised pseudo-label training[email protected] / [email protected]23.5 / 15.2Zoo3D paper, Table 2
ScanNet200Open-vocabulary 3D object detection (Zoo3D0 / Zoo3D1)Fully unposed multi-view images[email protected] / [email protected]8.3 / 2.9 (Zoo3D0); 10.7 / 3.8 (Zoo3D1)Zoo3D paper, Table 2
ARKitScenesOpen-vocabulary 3D object detection (Zoo3D0 / Zoo3D1)Point cloud and posed images[email protected] / [email protected]24.4 / 11.0 (Zoo3D0); 34.2 / 24.2 (Zoo3D1)Zoo3D paper, Table 15
ARKitScenesOpen-vocabulary 3D object detection (Zoo3D0 / Zoo3D1)Unposed multi-view images[email protected] / [email protected]13.0 / 2.6 (Zoo3D0); 16.1 / 3.5 (Zoo3D1)Zoo3D paper, Table 15

Values are attributed to the associated paper and the stated input and evaluation protocol.

Technologies and methods

  • CLIP
  • SAM 2.1
  • MaskClustering
  • DUSt3R
  • Sparse 3D detection

Related M:3L research

Evidence boundary

Benchmark claims and numerical values are paper-reported results for the named protocol. Potential applications are not evidence of completed deployments.