{"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/plug-and-play-improve-depth-estimation-via","title":"Plug-and-Play: Improve Depth Estimation via Sparse Data Propagation","arxiv_id":"1812.08350","date":"2018-12-20","proceeding":null,"authors":["Tsun-Hsuan Wang","Fu-En Wang","Juan-Ting Lin","Yi-Hsuan Tsai","Wei-Chen Chiu","Min Sun"],"abstract":"We propose a novel plug-and-play (PnP) module for improving depth prediction\nwith taking arbitrary patterns of sparse depths as input. Given any pre-trained\ndepth prediction model, our PnP module updates the intermediate feature map\nsuch that the model outputs new depths consistent with the given sparse depths.\nOur method requires no additional training and can be applied to practical\napplications such as leveraging both RGB and sparse LiDAR points to robustly\nestimate dense depth map. Our approach achieves consistent improvements on\nvarious state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e.,\nKITTI) datasets. Various types of LiDARs are also synthesized in our\nexperiments to verify the general applicability of our PnP module in practice.\nFor project page, see https://zswang666.github.io/PnP-Depth-Project-Page/","url_abs":"http://arxiv.org/abs/1812.08350v2","url_pdf":"http://arxiv.org/pdf/1812.08350v2.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":"plug-and-play-improve-depth-estimation-via","repo_url":"https://github.com/LakshmiTeja17/NNFL-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"plug-and-play-improve-depth-estimation-via","repo_url":"https://github.com/zswang666/PnP-Depth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.08350","atlas_url":"https://app.syntology.ai/?focus=1812.08350","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}