{"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/a-technique-to-jointly-estimate-depth-and","title":"A technique to jointly estimate depth and depth uncertainty for unmanned aerial vehicles","arxiv_id":"2305.19780","date":"2023-05-31","proceeding":null,"authors":["Michaël Fonder","Marc Van Droogenbroeck"],"abstract":"When used by autonomous vehicles for trajectory planning or obstacle avoidance, depth estimation methods need to be reliable. Therefore, estimating the quality of the depth outputs is critical. In this paper, we show how M4Depth, a state-of-the-art depth estimation method designed for unmanned aerial vehicle (UAV) applications, can be enhanced to perform joint depth and uncertainty estimation. For that, we present a solution to convert the uncertainty estimates related to parallax generated by M4Depth into uncertainty estimates related to depth, and show that it outperforms the standard probabilistic approach. Our experiments on various public datasets demonstrate that our method performs consistently, even in zero-shot transfer. Besides, our method offers a compelling value when compared to existing multi-view depth estimation methods as it performs similarly on a multi-view depth estimation benchmark despite being 2.5 times faster and causal, as opposed to other methods. The code of our method is publicly available at https://github.com/michael-fonder/M4DepthU .","url_abs":"https://arxiv.org/abs/2305.19780v1","url_pdf":"https://arxiv.org/pdf/2305.19780v1.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":"a-technique-to-jointly-estimate-depth-and","repo_url":"https://github.com/michael-fonder/m4depthu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"depth-aleatoric-uncertainty-estimation","task_name":"Depth Aleatoric Uncertainty Estimation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"trajectory-planning","task_name":"Trajectory Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-aleatoric-uncertainty-estimation-on-mid","task":"Depth Aleatoric Uncertainty Estimation","dataset":"Mid-Air Dataset","model":"M4Depth+U","rank_in_archive_order":1,"of":1,"metrics":{"AuSE on Abs Rel":"0.007","AuSE on RMSE log":"0.02"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-mid-air-dataset","task":"Monocular Depth Estimation","dataset":"Mid-Air Dataset","model":"M4Depth+U","rank_in_archive_order":1,"of":6,"metrics":{"Abs Rel":"0.134","RMSE log":"0.188"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}