Online Scene CAD Recomposition via Autonomous Scanning-Reference-Cited by-同舟云学术

Online Scene CAD Recomposition via Autonomous Scanning

Published:2023-12-05 Issue:6 Volume:42 Page:1-16
ISSN:0730-0301
Container-title:ACM Transactions on Graphics
language:en
Short-container-title:ACM Trans. Graph.

Author:

Li Changhao¹^ORCID,Guo Junfu¹^ORCID,Hu Ruizhen²^ORCID,Liu Ligang¹^ORCID

Affiliation:

1. University of Science and Technology of China, China

2. Shenzhen University, China

Abstract

Autonomous surface reconstruction of 3D scenes has been intensely studied in recent years, however, it is still difficult to accurately reconstruct all the surface details of complex scenes with complicated object relations and severe occlusions, which makes the reconstruction results not suitable for direct use in applications such as gaming and virtual reality. Therefore, instead of reconstructing the detailed surfaces, we aim to recompose the scene with CAD models retrieved from a given dataset to faithfully reflect the object geometry and arrangement in the given scene. Moreover, unlike most of the previous works on scene CAD recomposition requiring an offline reconstructed scene or captured video as input, which leads to significant data redundancy, we propose a novel online scene CAD recomposition method with autonomous scanning, which efficiently recomposes the scene with the guidance of automatically optimized Next-Best-View (NBV) in a single online scanning pass. Based on the key observation that spatial relation in the scene can not only constrain the object pose and layout optimization but also guide the NBV generation, our system consists of two key modules: relation-guided CAD recomposition module that uses relation-constrained global optimization to get accurate object pose and layout estimation, and relation-aware NBV generation module that makes the exploration during the autonomous scanning tailored for our composition task. Extensive experiments have been conducted to show the superiority of our method over previous methods in scanning efficiency and retrieval accuracy as well as the importance of each key component of our method.

Funder

National Key R&D Program of China

National Natural Science Foundation of China

GD Natural Science Foundation

Shenzhen Science and Technology Program

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design

Link

https://dl.acm.org/doi/pdf/10.1145/3618339

Reference53 articles.

1. Armen Avetisyan , Manuel Dahnert , Angela Dai , Manolis Savva , Angel X. Chang , and Matthias Nießner . 2018a. Scan2CAD: Learning CAD Model Alignment in RGB-D Scans. CoRR abs/1811.11187 ( 2018 ). arXiv:1811.11187 http://arxiv.org/abs/1811.11187 Armen Avetisyan, Manuel Dahnert, Angela Dai, Manolis Savva, Angel X. Chang, and Matthias Nießner. 2018a. Scan2CAD: Learning CAD Model Alignment in RGB-D Scans. CoRR abs/1811.11187 (2018). arXiv:1811.11187 http://arxiv.org/abs/1811.11187

2. Armen Avetisyan , Manuel Dahnert , Angela Dai , Manolis Savva , Angel X. Chang , and Matthias Nießner . 2018b. Scan2CAD: Learning CAD Model Alignment in RGB-D Scans. CoRR abs/1811.11187 ( 2018 ). arXiv:1811.11187 http://arxiv.org/abs/1811.11187 Armen Avetisyan, Manuel Dahnert, Angela Dai, Manolis Savva, Angel X. Chang, and Matthias Nießner. 2018b. Scan2CAD: Learning CAD Model Alignment in RGB-D Scans. CoRR abs/1811.11187 (2018). arXiv:1811.11187 http://arxiv.org/abs/1811.11187

3. Armen Avetisyan , Angela Dai , and Matthias Nießner . 2019. End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans. CoRR abs/1906.04201 ( 2019 ). arXiv:1906.04201 http://arxiv.org/abs/1906.04201 Armen Avetisyan, Angela Dai, and Matthias Nießner. 2019. End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans. CoRR abs/1906.04201 (2019). arXiv:1906.04201 http://arxiv.org/abs/1906.04201

4. Armen Avetisyan , Tatiana Khanova , Christopher B. Choy , Denver Dash , Angela Dai , and Matthias Nießner . 2020. SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans. CoRR abs/2003.12622 ( 2020 ). arXiv:2003.12622 https://arxiv.org/abs/2003.12622 Armen Avetisyan, Tatiana Khanova, Christopher B. Choy, Denver Dash, Angela Dai, and Matthias Nießner. 2020. SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans. CoRR abs/2003.12622 (2020). arXiv:2003.12622 https://arxiv.org/abs/2003.12622

5. A method for registration of 3-D shapes