{"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/self-supervised-monocular-depthestimation","title":"Self-Supervised Monocular Depth Estimation with Internal Feature Fusion","arxiv_id":"2110.09482","date":"2021-10-18","proceeding":null,"authors":["Hang Zhou","David Greenwood","Sarah Taylor"],"abstract":"Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial and semantic representations from images. Therefore, it is natural to exploit semantic segmentation networks for depth estimation. In this work, based on a well-developed semantic segmentation network HRNet, we propose a novel depth estimation network DIFFNet, which can make use of semantic information in down and upsampling procedures. By applying feature fusion and an attention mechanism, our proposed method outperforms the state-of-the-art monocular depth estimation methods on the KITTI benchmark. Our method also demonstrates greater potential on higher resolution training data. We propose an additional extended evaluation strategy by establishing a test set of challenging cases, empirically derived from the standard benchmark.","url_abs":"https://arxiv.org/abs/2110.09482v3","url_pdf":"https://arxiv.org/pdf/2110.09482v3.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":"self-supervised-monocular-depthestimation","repo_url":"https://github.com/brandleyzhou/diffnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"unsupervised-monocular-depth-estimation","task_name":"Unsupervised Monocular Depth Estimation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"hrnet","method_name":"HRNet"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"DIFFNet (MS+1024x320)","rank_in_archive_order":12,"of":55,"metrics":{"Delta < 1.25":"0.911","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.984","Mono":"X","RMSE":"4.250","RMSE log":"0.172","Sq Rel":"0.678","absolute relative error":"0.094"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.09482","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}