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

arXiv: https://arxiv.org/abs/2511.20253 · HTML: https://mlsanity.com/paper/2511.20253/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 46 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 30 of 42)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness](https://mlsanity.com/paper/2409.18125/) (2024)
- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)
- [VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction](https://mlsanity.com/paper/2505.20279/) (2025)
- [ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection](https://mlsanity.com/paper/2106.01178/) (2021)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding](https://mlsanity.com/paper/2412.00493/) (2024)
- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection](https://mlsanity.com/paper/2112.00322/) (2021)
- [Open-Vocabulary Point-Cloud Object Detection without 3D Annotation](https://mlsanity.com/paper/2304.00788/) (2023)
- [SpatialLM: Training Large Language Models for Structured Indoor Modeling](https://mlsanity.com/paper/2506.07491/) (2025)
- [MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2401.07745/) (2024)
- [CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection](https://mlsanity.com/paper/2310.02960/) (2023)
- [SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model](https://mlsanity.com/paper/2306.02245/) (2023)
- [LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences](https://mlsanity.com/paper/2412.01292/) (2024)
- [V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection](https://mlsanity.com/paper/2308.04409/) (2023)

## Built on by (most cited first, 4 of 4)

- [WorldSculpt: Generating Compositional Worlds from Grounded Videos](https://mlsanity.com/paper/2609.05416/) (2026)
- [Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection](https://mlsanity.com/paper/2603.21944/) (2026)
- [Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection](https://mlsanity.com/paper/2607.14560/) (2026)
- [Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding](https://mlsanity.com/paper/2608.21136/) (2026)

## Abstract (arXiv)

3D object detection is fundamental for spatial understanding. Real-world environments demand models capable of recognizing diverse, previously unseen objects, which remains a major limitation of closed-set methods. Existing open-vocabulary 3D detectors relax annotation requirements but still depend on training scenes, either as point clouds or images. We take this a step further by introducing Zoo3D, the first training-free 3D object detection framework. Our method constructs 3D bounding boxes via graph clustering of 2D instance masks, then assigns semantic labels using a novel open-vocabulary module with best-view selection and view-consensus mask generation. Zoo3D operates in two modes: the zero-shot Zoo3D0, which requires no training at all, and the self-supervised Zoo3D1, which refines 3D box prediction by training a class-agnostic detector on Zoo3D0-generated pseudo labels. Furthermore, we extend Zoo3D beyond point clouds to work directly with posed and even unposed images. Across ScanNet200 and ARKitScenes benchmarks, both Zoo3D0 and Zoo3D1 achieve state-of-the-art results in open-vocabulary 3D object detection. Remarkably, our zero-shot Zoo3D0 outperforms all existing self-supervised methods, hence demonstrating the power and adaptability of training-free, off-the-shelf approaches for real-world 3D understanding. Code is available at https://github.com/col14m/zoo3d .