CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene
Abstract
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions. It is based on an end-to-end sparse convolutional network, CircNet, which jointly models local geometric details and global scene structural contexts, allowing it to preserve fine-grained object detail while recovering missing regions commonly arising in traditional 3D scene data. A novel differentiable rendering module further enables a test-time refinement for better reconstruction quality. Extensive experiments on both real-world and synthetic datasets show that our concise framework is effective, achieving better reconstruction quality while being significantly faster.
Cite
Text
Chen et al. "CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19824-3_30Markdown
[Chen et al. "CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/chen2022eccv-circle/) doi:10.1007/978-3-031-19824-3_30BibTeX
@inproceedings{chen2022eccv-circle,
title = {{CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene}},
author = {Chen, Hao-Xiang and Huang, Jiahui and Mu, Tai-Jiang and Hu, Shi-Min},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-19824-3_30},
url = {https://mlanthology.org/eccv/2022/chen2022eccv-circle/}
}