# DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation

arXiv: https://arxiv.org/abs/2503.18944 · HTML: https://mlsanity.com/paper/2503.18944/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 76 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 30 of 67)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [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)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)

## Built on by (most cited first, 30 of 31)

- [Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations](https://mlsanity.com/paper/2510.23607/) (2025)
- [C3G: Learning Compact 3D Representations with 2K Gaussians](https://mlsanity.com/paper/2512.04021/) (2025)
- [PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding](https://mlsanity.com/paper/2601.02457/) (2026)
- [SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features](https://mlsanity.com/paper/2509.16098/) (2025)
- [Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding](https://mlsanity.com/paper/2604.19609/) (2026)
- [Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-training](https://mlsanity.com/paper/2511.18115/) (2025)
- [DOS: Distilling Observable Softmaps of Zipfian Prototypes for Self-Supervised Point Representation](https://mlsanity.com/paper/2512.11465/) (2025)
- [Feasibility of Indoor Frame-Wise Lidar Semantic Segmentation via Distillation from Visual Foundation Model](https://mlsanity.com/paper/2604.18831/) (2026)
- [Analogical Trajectory Transfer](https://mlsanity.com/paper/2605.14393/) (2026)
- [A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2605.17131/) (2026)
- [Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models](https://mlsanity.com/paper/2606.21292/) (2026)
- [Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs](https://mlsanity.com/paper/2608.12179/) (2026)
- [Technical Report for ICRA 2025 GOOSE 3D Semantic Segmentation Challenge: Adaptive Point Cloud Understanding for Heterogeneous Robotic Systems](https://mlsanity.com/paper/2506.06995/) (2025)
- [FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction](https://mlsanity.com/paper/2509.14739/) (2025)
- [RangeSAM: On the Potential of Visual Foundation Models for Range-View represented LiDAR segmentation](https://mlsanity.com/paper/2509.15886/) (2025)
- [GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure](https://mlsanity.com/paper/2601.13052/) (2026)
- [On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training](https://mlsanity.com/paper/2601.18929/) (2026)
- [Bridging the Dimensionality Gap: A Taxonomy and Survey of 2D Vision Model Adaptation for 3D Analysis](https://mlsanity.com/paper/2604.03334/) (2026)
- [Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labeling](https://mlsanity.com/paper/2604.11007/) (2026)
- [Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation](https://mlsanity.com/paper/2604.23604/) (2026)
- [Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysis](https://mlsanity.com/paper/2605.02357/) (2026)
- [Mono-Hydra++: Real-Time Monocular Scene Graph Construction with Multi-Task Learning for 3D Indoor Mapping](https://mlsanity.com/paper/2605.17661/) (2026)
- [DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models](https://mlsanity.com/paper/2605.26949/) (2026)
- [Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning](https://mlsanity.com/paper/2605.29661/) (2026)
- [xModel-KD: Cross-modal Knowledge Distillation for 3D Scene Perception using LiDAR](https://mlsanity.com/paper/2605.30111/) (2026)
- [Vanilla ViT for Automotive Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2605.31177/) (2026)
- [Vernata: Self-Supervised Learning of LiDAR Point Representations](https://mlsanity.com/paper/2608.06919/) (2026)
- [DINO-3DRA: Leveraging 2D Foundation Model Semantics for 3D Cerebral Aneurysm Segmentation](https://mlsanity.com/paper/2608.07767/) (2026)
- [GraphWrit3R: End-to-End 3D Scene Graph Writing](https://mlsanity.com/paper/2609.31595/) (2026)
- [Learning Semantic Inpainting for Animatable Gaussian Head Avatars](https://mlsanity.com/paper/2609.38343/) (2026)

## Abstract (arXiv)

Vision foundation models (VFMs) trained on large-scale image datasets provide high-quality features that have significantly advanced 2D visual recognition. However, their potential in 3D scene segmentation remains largely untapped, despite the common availability of 2D images alongside 3D point cloud datasets. While significant research has been dedicated to 2D-3D fusion, recent state-of-the-art 3D methods predominantly focus on 3D data, leaving the integration of VFMs into 3D models underexplored. In this work, we challenge this trend by introducing DITR, a generally applicable approach that extracts 2D foundation model features, projects them to 3D, and finally injects them into a 3D point cloud segmentation model. DITR achieves state-of-the-art results on both indoor and outdoor 3D semantic segmentation benchmarks. To enable the use of VFMs even when images are unavailable during inference, we additionally propose to pretrain 3D models by distilling 2D foundation models. By initializing the 3D backbone with knowledge distilled from 2D VFMs, we create a strong basis for downstream 3D segmentation tasks, ultimately boosting performance across various datasets.