# VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM

arXiv: https://arxiv.org/abs/2609.00775 · HTML: https://mlsanity.com/paper/2609.00775/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 35 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [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)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping](https://mlsanity.com/paper/1910.02490/) (2019)
- [CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory](https://mlsanity.com/paper/2210.05663/) (2022)
- [VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold](https://mlsanity.com/paper/2505.12549/) (2025)
- [Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance](https://mlsanity.com/paper/2312.10671/) (2023)
- [PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things](https://mlsanity.com/paper/1903.01177/) (2019)
- [OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data](https://mlsanity.com/paper/2311.02873/) (2023)
- [Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation](https://mlsanity.com/paper/2310.03923/) (2023)
- [Multi-Modal Classifiers for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.05493/) (2023)
- [Open-Vocabulary Online Semantic Mapping for SLAM](https://mlsanity.com/paper/2411.15043/) (2024)
- [Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos](https://mlsanity.com/paper/2507.22052/) (2025)
- [OpenVox: Real-time Instance-level Open-vocabulary Probabilistic Voxel Representation](https://mlsanity.com/paper/2502.16528/) (2025)
- [TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models](https://mlsanity.com/paper/2505.23769/) (2025)
- [OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics](https://mlsanity.com/paper/2512.08625/) (2025)
- [OVI-MAP:Open-Vocabulary Instance-Semantic Mapping](https://mlsanity.com/paper/2603.26541/) (2026)

## Abstract (arXiv)

We present Voxel-Grounded Online Instance Manager (VOIM), a training-free voxel-grounded instance manager that builds open-vocabulary 3D instance maps from RGB-D or from monocular RGB alone, a regime no prior training-free system addresses. Online systems typically segment object instances and label them at first detection, committing when evidence is weakest. VOIM instead defers label and instance decisions until soft evidence from unmodified, off-the-shelf perception has accumulated per voxel across views. We show that the mapping stage, rather than the particular perception models, carries the result: across four perception configurations on ScanNet++, varying the region descriptor, the detector label prior and the mask source, the map exceeds the strongest online RGB-D system, OVO-SLAM, by between 4.8 and 11.7 mIoU. Perception is not neutral, and substituting that baseline's own descriptor family costs 4.1 of the margin, yet the baseline carries the marginally better 2D descriptor (33.7 vs. 31.5 mIoU over three scenes) and still realizes the weaker map. Under a like-for-like protocol VOIM reaches 44.07 mIoU on ScanNet++ against 32.37, winning all ten scenes and both aggregations (pooled 33.31 vs. 25.97), and the same system runs unchanged to fully monocular RGB, matching that baseline pooled on Replica (27.80 vs. 27.50). The advantage is regime-specific: under Replica's all-classes scoring, matched inputs give a split result, 28.60 vs. 27.50 pooled against 24.59 vs. 30.11 on the per-scene mean. Room scale is label-limited and building scale drift-limited. Labeling does not run in real time, dominated by per-class detection over the full vocabulary. The maps export occupancy grids and resolve free-form queries to object instances.