{"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/r-msfm-recurrent-multi-scale-feature","title":"R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating","arxiv_id":null,"date":"2021-01-01","proceeding":"ICCV 2021 10","authors":["Zhongkai Zhou","Xinnan Fan","Pengfei Shi","Yuanxue Xin"],"abstract":"    In this paper, we propose Recurrent Multi-Scale Feature Modulation (R-MSFM), a new deep network architecture for self-supervised monocular depth estimation. R-MSFM extracts per-pixel features, builds a multi-scale feature modulation module, and iteratively updates an inverse depth through a parameter-shared decoder at the fixed resolution. This architecture enables our R-MSFM to maintain semantically richer while spatially more precise representations and avoid the error propagation caused by the traditional U-Net-like coarse-to-fine architecture widely used in this domain, resulting in strong generalization and efficient parameter count. Experimental results demonstrate the superiority of our proposed R-MSFM both at model size and inference speed, and show the state-of-the-art results on the KITTI benchmark. Code is available at https://github.com/jsczzzk/R-MSFM    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2021/html/Zhou_R-MSFM_Recurrent_Multi-Scale_Feature_Modulation_for_Monocular_Depth_Estimating_ICCV_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2021/papers/Zhou_R-MSFM_Recurrent_Multi-Scale_Feature_Modulation_for_Monocular_Depth_Estimating_ICCV_2021_paper.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":"r-msfm-recurrent-multi-scale-feature","repo_url":"https://github.com/jsczzzk/r-msfm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}