This repository contains the implementation of our ECCV 2022 paper: CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene.
Haoxiang Chen, Jiahui Huang, Tai-Jiang Mu, Shi-Min Hu
CIRCLE is a framework for large-scale scene completion and geometric refinement based on local implicit signed distance function. Please refer to our technical report for more details.
We now provide implementation based on Pytorch and we will soon provide jittor version which is faster for training.
Please refer to the corresponding folders jittor/ and pytorch/ for specific build and running instructions.
If you find this reposity is useful, please cite our paper: Haoxiang Chen, Jiahui Huang, Tai-Jiang Mu, Shi-Min Hu: CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene. ECCV (32) 2022: 506-522