Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions

2020-04-08 · CVPR 2020 6 · Johanna Wald, Helisa Dhamo, Nassir Navab, Federico Tombari

Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic segmentation and scene layout prediction. In our work we focus on scene graphs, a data structure that organizes the entities of a scene in a graph, where objects are nodes and their relationships modeled as edges. We leverage inference on scene graphs as a way to carry out 3D scene understanding, mapping objects and their relationships. In particular, we propose a learned method that regresses a scene graph from the point cloud of a scene. Our novel architecture is based on PointNet and Graph Convolutional Networks (GCN). In addition, we introduce 3DSSG, a semi-automatically generated dataset, that contains semantically rich scene graphs of 3D scenes. We show the application of our method in a domain-agnostic retrieval task, where graphs serve as an intermediate representation for 3D-3D and 2D-3D matching.

📄 PDF Abstract BibTeX arXiv:2004.03967

Code (0)

등록된 구현이 없습니다.

Tasks

3d scene graph generation3D Semantic Segmentation Retrieval Scene Understanding Semantic Segmentation

Methods 이 논문이 사용한 방법론

Graph Convolutional Networks 설명 없음

eToro Customer Care Number +1-833-534-1729 설명 없음

PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes

2022-07-02 · CVPR 2022 1 · Yu-Ying Yeh, Zhengqin Li, Yannick Hold-Geoffroy, Rui Zhu 외

Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout. In this work, we go beyond this to propose PhotoScene, a framework that takes input image(s) of a scene along with approximate…

3D geometry 3D Scene Reconstruction

OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions

2025-03-13 · Maxim Popov, Regina Kurkova, Mikhail Iumanov, Jaafar Mahmoud 외

Open Semantic Mapping (OSM) is a key technology in robotic perception, combining semantic segmentation and SLAM techniques. This paper introduces a dynamically configurable and highly automated LLM/LVLM-powered pipeline …

Object Recognition Semantic Segmentation

LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction

2026-05-13 · Christina Kassab, Hyeonjae Gil, Matías Mattamala, Ayoung Kim 외 arxiv

Scene graphs are becoming a standard representation for robot navigation, providing hierarchical geometric and semantic scene understanding. However, most scene graph mapping methods rely on depth cameras or LiDAR sensor…

Object Segmentation Scene Understanding Robot Navigation

ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes

2017-02-14 · CVPR 2017 7 · Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber 외

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datas…

3D Object Classification General Classification Retrieval Scene Understanding+2

ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

2023-08-22 · ICCV 2023 1 · Chandan Yeshwanth, Yueh-Cheng Liu, Matthias Nießner, Angela Dai

We present ScanNet++, a large-scale dataset that couples together capture of high-quality and commodity-level geometry and color of indoor scenes. Each scene is captured with a high-end laser scanner at sub-millimeter re…

3D Semantic Segmentation Novel View Synthesis Scene Understanding