# GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contraction

arXiv: https://arxiv.org/abs/2504.03129 · HTML: https://mlsanity.com/paper/2504.03129/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 47 references that are in the map.
- First posted on arXiv 4 Apr 2025.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [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)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [OccuSeg: Occupancy-aware 3D Instance Segmentation](https://mlsanity.com/paper/2003.06537/) (2020)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance](https://mlsanity.com/paper/2312.10671/) (2023)
- [Grasp Pose Detection in Point Clouds](https://mlsanity.com/paper/1706.09911/) (2017)
- [Bidirectional Projection Network for Cross Dimension Scene Understanding](https://mlsanity.com/paper/2103.14326/) (2021)
- [High-Quality Entity Segmentation](https://mlsanity.com/paper/2211.05776/) (2022)
- [OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data](https://mlsanity.com/paper/2311.02873/) (2023)
- [MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2401.07745/) (2024)
- [Point-SAM: Promptable 3D Segmentation Model for Point Clouds](https://mlsanity.com/paper/2406.17741/) (2024)
- [DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark](https://mlsanity.com/paper/2403.10814/) (2024)
- [RecGS: Removing Water Caustic with Recurrent Gaussian Splatting](https://mlsanity.com/paper/2407.10318/) (2024)
- [Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching](https://mlsanity.com/paper/2309.03835/) (2023)

## Built on by (most cited first, 2 of 2)

- [Bi-Manual Joint Camera Calibration and Scene Representation](https://mlsanity.com/paper/2505.24819/) (2025)
- [Clutt3R-Seg: Sparse-view 3D Instance Segmentation for Language-grounded Grasping in Cluttered Scenes](https://mlsanity.com/paper/2602.11660/) (2026)

## Abstract (arXiv)

Robots operating in unstructured environments often require accurate and consistent object-level representations. This typically requires segmenting individual objects from the robot's surroundings. While recent large models such as Segment Anything (SAM) offer strong performance in 2D image segmentation. These advances do not translate directly to performance in the physical 3D world, where they often over-segment objects and fail to produce consistent mask correspondences across views. In this paper, we present GraphSeg, a framework for generating consistent 3D object segmentations from a sparse set of 2D images of the environment without any depth information. GraphSeg adds edges to graphs and constructs dual correspondence graphs: one from 2D pixel-level similarities and one from inferred 3D structure. We formulate segmentation as a problem of edge addition, then subsequent graph contraction, which merges multiple 2D masks into unified object-level segmentations. We can then leverage 3D foundation models to produce segmented 3D representations. GraphSeg achieves robust segmentation with significantly fewer images and greater accuracy than prior methods. We demonstrate state-of-the-art performance on tabletop scenes and show that GraphSeg enables improved performance on downstream robotic manipulation tasks. Code available at https://github.com/tomtang502/graphseg.git.