{"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/d-net-a-generalised-and-optimised-deep","title":"D-Net: A Generalised and Optimised Deep Network for Monocular Depth Estimation","arxiv_id":null,"date":"2021-09-29","proceeding":"IEEE Access 2021 9","authors":["Joshua Luke Thompson","Son Lam Phung","Abdesselam Bouzerdoum"],"abstract":"Depth estimation is an essential component in computer vision systems for achieving 3D scene understanding. Efficient and accurate depth map estimation has numerous applications including self-driving vehicles and virtual reality tools. This paper presents a new deep network, called D-Net, for depth estimation from a single RGB image. The proposed network can be trained end-to-end, and its structure can be customised to meet different requirements in model size, speed, and prediction accuracy. Our approach gathers strong global and local contextual features at multiple resolutions, and then transfers these to high resolutions for clearer depth maps. For the encoder backbone, D-Net can utilise many state-of-the-art models including EfficientNet, HRNet and Swin Transformer to obtain dense depth maps. The proposed D-net is designed to have minimal parameters and reduced computational complexity. Extensive evaluations on the NYUv2 and KITTI benchmark datasets show that our model is highly accurate across multiple backbones, and it achieves state-of-the-art performance on both benchmarks when combined with the Swin Transformer and HRNets.","url_abs":"https://ieeexplore.ieee.org/document/9551940","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9551940","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":"d-net-a-generalised-and-optimised-deep","repo_url":"https://github.com/Joshuat38/D-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"D-Net","rank_in_archive_order":31,"of":79,"metrics":{"Delta < 1.25":"0.963","Delta < 1.25^2":"0.995","Delta < 1.25^3":"0.999","RMSE":"2.362","RMSE log":"0.087","Sq Rel":"0.189","absolute relative error":"0.056"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"D-Net","rank_in_archive_order":44,"of":85,"metrics":{"Delta < 1.25":"0.919","Delta < 1.25^2":"0.988","Delta < 1.25^3":"0.997","RMSE":"0.354","absolute relative error":"0.095","log 10":"0.041"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}