# ODIN: A Single Model for 2D and 3D Segmentation

arXiv: https://arxiv.org/abs/2401.02416 · HTML: https://mlsanity.com/paper/2401.02416/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 61 references that are in the map.
- First posted on arXiv 4 Jan 2024.

## Builds on (most cited first, 30 of 56)

- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [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)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Graph Neural Networks with Learnable Structural and Positional Representations](https://mlsanity.com/paper/2110.07875/) (2021)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Omnivore: A Single Model for Many Visual Modalities](https://mlsanity.com/paper/2201.08377/) (2022)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)

## Built on by (most cited first, 25 of 25)

- [LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness](https://mlsanity.com/paper/2409.18125/) (2024)
- [TAPIP3D: Tracking Any Point in Persistent 3D Geometry](https://mlsanity.com/paper/2504.14717/) (2025)
- [DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation](https://mlsanity.com/paper/2503.18944/) (2025)
- [Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D](https://mlsanity.com/paper/2504.14151/) (2025)
- [3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation](https://mlsanity.com/paper/2508.11002/) (2025)
- [Unifying 2D and 3D Vision-Language Understanding](https://mlsanity.com/paper/2503.10745/) (2025)
- [RayRoPE: Projective Ray Positional Encoding for Multi-view Attention](https://mlsanity.com/paper/2601.15275/) (2026)
- [Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds](https://mlsanity.com/paper/2602.00807/) (2026)
- [A Survey on Multimodal Wearable Sensor-based Human Action Recognition](https://mlsanity.com/paper/2404.15349/) (2024)
- [From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs](https://mlsanity.com/paper/2502.20389/) (2025)
- [SAB3R: Semantic-Augmented Backbone in 3D Reconstruction](https://mlsanity.com/paper/2506.02112/) (2025)
- [Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding](https://mlsanity.com/paper/2608.02980/) (2026)
- [SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features](https://mlsanity.com/paper/2509.16098/) (2025)
- [OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction](https://mlsanity.com/paper/2509.23541/) (2025)
- [3AM: 3egment Anything with Geometric Consistency in Videos](https://mlsanity.com/paper/2601.08831/) (2026)
- [Formula-Supervised Visual-Geometric Pre-training](https://mlsanity.com/paper/2409.13535/) (2024)
- [Pts3D-LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models](https://mlsanity.com/paper/2506.05689/) (2025)
- [SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images](https://mlsanity.com/paper/2603.19926/) (2026)
- [Pixels2Points: Fusing 2D and 3D Features for Facial Skin Segmentation](https://mlsanity.com/paper/2504.19718/) (2025)
- [Pano3D: Unified 3D Reconstruction and Panoptic Segmentation](https://mlsanity.com/paper/2606.14307/) (2026)
- [SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation](https://mlsanity.com/paper/2609.25490/) (2026)
- [Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2506.22817/) (2025)
- [SNAP: Towards Segmenting Anything in Any Point Cloud](https://mlsanity.com/paper/2510.11565/) (2025)
- [G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation](https://mlsanity.com/paper/2601.03510/) (2026)
- [Generalizable Human Gaussian Splatting via Multi-view Semantic Consistency](https://mlsanity.com/paper/2604.25466/) (2026)

## Abstract (arXiv)

State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB-D multiview images instead. The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature operations through the positional encodings of the tokens involved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It outperforms all previous works by a wide margin when the sensed 3D point cloud is used in place of the point cloud sampled from 3D mesh. When used as the 3D perception engine in an instructable embodied agent architecture, it sets a new state-of-the-art on the TEACh action-from-dialogue benchmark. Our code and checkpoints can be found at the project website (https://odin-seg.github.io).