# Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation

arXiv: https://arxiv.org/abs/2502.02548 · HTML: https://mlsanity.com/paper/2502.02548/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 97 of its 115 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Builds on (most cited first, 30 of 97)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)

## Built on by (most cited first, 22 of 22)

- [SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining](https://mlsanity.com/paper/2503.18052/) (2025)
- [Multiplayer Interactive World Models with Representation Autoencoders](https://mlsanity.com/paper/2607.05352/) (2026)
- [SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting](https://mlsanity.com/paper/2506.08710/) (2025)
- [Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding](https://mlsanity.com/paper/2512.17817/) (2025)
- [Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale](https://mlsanity.com/paper/2506.12009/) (2025)
- [OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2601.09575/) (2026)
- [GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis](https://mlsanity.com/paper/2603.14965/) (2026)
- [The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models](https://mlsanity.com/paper/2601.08876/) (2026)
- [SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2604.20395/) (2026)
- [OpenLex3D: A Tiered Evaluation Benchmark for Open-Vocabulary 3D Scene Representations](https://mlsanity.com/paper/2503.19764/) (2025)
- [Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenization](https://mlsanity.com/paper/2505.18819/) (2025)
- [GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation](https://mlsanity.com/paper/2603.26260/) (2026)
- [Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applications](https://mlsanity.com/paper/2607.00978/) (2026)
- [Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting](https://mlsanity.com/paper/2512.20927/) (2025)
- [FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation](https://mlsanity.com/paper/2605.27178/) (2026)
- [Training-Free Open-Vocabulary 3D Point-Cloud Segmentation on the Generalized Few-Shot Benchmark](https://mlsanity.com/paper/2607.15331/) (2026)
- [Beyond Similarity Matching: Structured Reasoning for Open-Vocabulary Referring Segmentation in 3DGS](https://mlsanity.com/paper/2608.16103/) (2026)
- [GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting](https://mlsanity.com/paper/2609.09082/) (2026)
- [From Alignment to Fusion in 3D Vision-Language](https://mlsanity.com/paper/2609.28222/) (2026)
- [GraphWrit3R: End-to-End 3D Scene Graph Writing](https://mlsanity.com/paper/2609.31595/) (2026)
- [PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation](https://mlsanity.com/paper/2610.02840/) (2026)
- [UMAS3D: Unified Mask-Free 3D Editing with Region-Adaptive Source Preservation](https://mlsanity.com/paper/2610.15533/) (2026)

## Abstract (arXiv)

We tackle open-vocabulary 3D scene understanding by introducing a novel data generation pipeline and training framework. Our method addresses three critical requirements for effective training: precise 3D region segmentation, comprehensive textual descriptions, and sufficient dataset scale. By leveraging state-of-the-art open-vocabulary image segmentation models and region-aware Vision-Language Models, we develop an automatic pipeline that generates high-quality 3D mask-text pairs. Applying this pipeline to multiple 3D scene datasets, we create Mosaic3D-5.6M, a dataset of over 30K annotated scenes with 5.6M mask-text pairs, significantly larger than existing datasets. Building upon this data, we propose Mosaic3D, a foundation model combining a 3D encoder trained with contrastive learning and a lightweight mask decoder for open-vocabulary 3D semantic and instance segmentation. Our approach achieves state-of-the-art results on open-vocabulary 3D semantic and instance segmentation tasks including ScanNet200, Matterport3D, and ScanNet++, with ablation studies validating the effectiveness of our large-scale training data.