Year: 2021
Type: conference-paper
Abstract: Aligning partial views of a scene into a single whole is essential to understanding one’s environment and is a key component of numerous robotics tasks such as SLAM and SfM. Recent approaches have proposed end-to-end systems that can outperform traditional methods by leveraging pose supervision. However, with the rising prevalence of cameras with depth sensors, we can expect a new stream of raw RGB-D data without the annotations needed for supervision. We propose UnsupervisedR&R: an end-to-end unsupervised approach to learning point cloud registration from raw RGB-D video. The key idea is to leverage differentiable alignment and rendering to enforce photometric and geometric consistency between frames. We evaluate our approach on indoor scene datasets and find that we out-perform existing traditional approaches with classical and learned descriptors while being competitive with supervised geometric point cloud registration approaches.
Authors: Mohamed El Banani, Luya Gao, Justin Johnson
Institution: University of Michigan
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3179294165