{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pose-constraints-for-consistent-self","title":"Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion","arxiv_id":"2304.08916","date":"2023-04-18","proceeding":null,"authors":["Zeeshan Khan Suri"],"abstract":"Self-supervised monocular depth estimation approaches suffer not only from scale ambiguity but also infer temporally inconsistent depth maps w.r.t. scale. While disambiguating scale during training is not possible without some kind of ground truth supervision, having scale consistent depth predictions would make it possible to calculate scale once during inference as a post-processing step and use it over-time. With this as a goal, a set of temporal consistency losses that minimize pose inconsistencies over time are introduced. Evaluations show that introducing these constraints not only reduces depth inconsistencies but also improves the baseline performance of depth and ego-motion prediction.","url_abs":"https://arxiv.org/abs/2304.08916v1","url_pdf":"https://arxiv.org/pdf/2304.08916v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pose-constraints-for-consistent-self","repo_url":"https://github.com/zshn25/pc4consistentdepth","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"camera-pose-estimation","task_name":"Camera Pose Estimation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"egocentric-pose-estimation","task_name":"Egocentric Pose Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"unsupervised-monocular-depth-estimation","task_name":"Unsupervised Monocular Depth Estimation"},{"task_slug":"motion-prediction","task_name":"motion prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/egocentric-pose-estimation-on-kitti-odometry","task":"Egocentric Pose Estimation","dataset":"Kitti Odometry","model":"pc4consistentdepth","rank_in_archive_order":1,"of":1,"metrics":{"Absolute Trajectory Error [m]":"0.014"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"pc4consistentdepth","rank_in_archive_order":51,"of":55,"metrics":{"absolute relative error":"0.113"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}