CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene
This work addresses scene completion and refinement for 3D indoor environments, offering significant speed improvements, though it appears incremental in method.
The authors tackled the problem of large-scale indoor scene completion and geometric refinement by introducing CIRCLE, a framework based on local implicit signed distance functions and an end-to-end sparse convolutional network, achieving better reconstruction quality than the closest competitor while being 10-50x faster.
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, that 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 enables test-time refinement for better reconstruction quality. Extensive experiments on both real-world and synthetic datasets show that our concise framework is efficient and effective, achieving better reconstruction quality than the closest competitor while being 10-50x faster.