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

arXiv: https://arxiv.org/abs/2508.20063 · HTML: https://mlsanity.com/paper/2508.20063/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 66 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 30 of 58)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)

## Built on by (most cited first, 7 of 7)

- [Zoo3D: Zero-Shot 3D Object Detection at Scene Level](https://mlsanity.com/paper/2511.20253/) (2025)
- [Generative Refocusing: Flexible Defocus Control from a Single Image](https://mlsanity.com/paper/2512.16923/) (2025)
- [3AM: 3egment Anything with Geometric Consistency in Videos](https://mlsanity.com/paper/2601.08831/) (2026)
- [Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models](https://mlsanity.com/paper/2512.21337/) (2025)
- [Auto-Vocabulary 3D Object Detection](https://mlsanity.com/paper/2512.16077/) (2025)
- [Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection](https://mlsanity.com/paper/2603.21944/) (2026)
- [Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding](https://mlsanity.com/paper/2608.21136/) (2026)

## Abstract (arXiv)

Open-vocabulary (OV) 3D object detection is an emerging field, yet its exploration through image-based methods remains limited compared to 3D point cloud-based methods. We introduce OpenM3D, a novel open-vocabulary multi-view indoor 3D object detector trained without human annotations. In particular, OpenM3D is a single-stage detector adapting the 2D-induced voxel features from the ImGeoNet model. To support OV, it is jointly trained with a class-agnostic 3D localization loss requiring high-quality 3D pseudo boxes and a voxel-semantic alignment loss requiring diverse pre-trained CLIP features. We follow the training setting of OV-3DET where posed RGB-D images are given but no human annotations of 3D boxes or classes are available. We propose a 3D Pseudo Box Generation method using a graph embedding technique that combines 2D segments into coherent 3D structures. Our pseudo-boxes achieve higher precision and recall than other methods, including the method proposed in OV-3DET. We further sample diverse CLIP features from 2D segments associated with each coherent 3D structure to align with the corresponding voxel feature. The key to training a highly accurate single-stage detector requires both losses to be learned toward high-quality targets. At inference, OpenM3D, a highly efficient detector, requires only multi-view images for input and demonstrates superior accuracy and speed (0.3 sec. per scene) on ScanNet200 and ARKitScenes indoor benchmarks compared to existing methods. We outperform a strong two-stage method that leverages our class-agnostic detector with a ViT CLIP-based OV classifier and a baseline incorporating multi-view depth estimator on both accuracy and speed.