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

2025-04-04 · Haozhan Tang, Tianyi Zhang, Oliver Kroemer, Matthew Johnson-Roberson, Weiming Zhi

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 \emph{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.

📄 PDF Abstract BibTeX arXiv:2504.03129

Code (1)

tomtang502/graphseg 공식 구현

Tasks

Image Segmentation Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Addressing Graph Anomaly Detection via Causal Edge Separation and Spectrum

2025-08-20 · Zengyi Wo, Wenjun Wang, Minglai Shao, Chang Liu 외 arxiv

In the real world, anomalous entities often add more legitimate connections while hiding direct links with other anomalous entities, leading to heterophilic structures in anomalous networks that most GNN-based techniques…

Graph Anomaly Detection

Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network

2021-09-11 · Naina Dhingra, George Chogovadze, Andreas Kunz

We present Border-SegGCN, a novel architecture to improve semantic segmentation by refining the border outline using graph convolutional networks (GCN). The semantic segmentation network such as Unet or DeepLabV3+ is use…

Segmentation Semantic Segmentation

FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG

2026-02-01 · Mengzhu Chen, Haodong Yang, Jia Cai, Xiaolin Huang arxiv

Retrieval-Augmented Generation (RAG) systems critically depend on how external knowledge is segmented, structured, and retrieved. Most existing approaches either retrieve fixed-length text chunks, which fragments discour…

Segmented Graph-Bert for Graph Instance Modeling

2020-02-09 · Jiawei Zhang

In graph instance representation learning, both the diverse graph instance sizes and the graph node orderless property have been the major obstacles that render existing representation learning models fail to work. In th…

Graph Classification Representation Learning

Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentation

2021-08-06 · Ufuk Demir, Atahan Ozer, Yusuf H. Sahin, Gozde Unal

In recent years, deep learning based methods have shown success in essential medical image analysis tasks such as segmentation. Post-processing and refining the results of segmentation is a common practice to decrease th…

Computed Tomography (CT)Medical Image Analysis Pancreas Segmentation Segmentation