Unsupervised Depth Completion from Visual Inertial Odometry · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1905.08616/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTUnsupervised Depth Completion from Visual Inertial Odometry — HN submissionhttps://news.ycombinator.com/item?id=28360018urn:hackerpapers:submission:1905.08616:28360018Mon, 30 Aug 2021 19:42:13 GMT<p>ICRA2020: Unsupervised Depth Completion from Visual Inertial Odometry</p><p>Hey there, interested in camera and range sensor fusion for point cloud (depth) completion? Here is an extended version of our [talk](https://www.youtube.com/watch?v=oBCKO4TH5y0) at ICRA 2020 where we do a step by step walkthrough of our paper Unsupervised Depth Completion from Visual Inertial Odometry (joint work with Fei Xiaohan, Stephanie Tsuei, and Stefano Soatto). In this talk, we present an unsupervised method (no need for human supervision/annotations) for learning to recover dense point clouds from images, captured by cameras, and sparse point clouds, produced by lidar or tracked by…</p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1905.08616/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CV