{"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/semantically-guided-representation-learning-1","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","arxiv_id":"2002.12319","date":"2020-02-27","proceeding":"ICLR 2020 1","authors":["Vitor Guizilini","Rui Hou","Jie Li","Rares Ambrus","Adrien Gaidon"],"abstract":"Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appearance to 3D properties by implicitly leveraging category-level patterns. In this work we investigate how to leverage more directly this semantic structure to guide geometric representation learning, while remaining in the self-supervised regime. Instead of using semantic labels and proxy losses in a multi-task approach, we propose a new architecture leveraging fixed pretrained semantic segmentation networks to guide self-supervised representation learning via pixel-adaptive convolutions. Furthermore, we propose a two-stage training process to overcome a common semantic bias on dynamic objects via resampling. Our method improves upon the state of the art for self-supervised monocular depth prediction over all pixels, fine-grained details, and per semantic categories.","url_abs":"https://arxiv.org/abs/2002.12319v1","url_pdf":"https://arxiv.org/pdf/2002.12319v1.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":"semantically-guided-representation-learning-1","repo_url":"https://github.com/TRI-ML/packnet-sfm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.12319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12319"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TRI-ML/packnet-sfm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3f9936537c112aa9","entry":"construct_K","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/geometry/camera_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/geometry/camera_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f9936537c112aa9"}},{"code_sha256_prefix":"56344348062c1db9","entry":"dummy_calibration","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/datasets/image_dataset.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/datasets/image_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"56344348062c1db9"}},{"code_sha256_prefix":"a4c5f47d2c6efb9c","entry":"euler2mat","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/geometry/pose_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/geometry/pose_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4c5f47d2c6efb9c"}},{"code_sha256_prefix":"6d3ca8f94497d761","entry":"get_idx","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/datasets/image_dataset.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/datasets/image_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d3ca8f94497d761"}},{"code_sha256_prefix":"1ec4bb6cee548217","entry":"invert_pose","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/geometry/pose_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/geometry/pose_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ec4bb6cee548217"}},{"code_sha256_prefix":"e077e60a96f5a927","entry":"pose_vec2mat","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/geometry/pose_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/geometry/pose_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e077e60a96f5a927"}},{"code_sha256_prefix":"bdf83cb105e62b4d","entry":"read_files","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/datasets/image_dataset.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/datasets/image_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdf83cb105e62b4d"}},{"code_sha256_prefix":"1c9d1d852e11deaf","entry":"read_npz_depth","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/datasets/kitti_dataset.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/datasets/kitti_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c9d1d852e11deaf"}},{"code_sha256_prefix":"837c6a474dd26eff","entry":"resize_depth","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/datasets/augmentations.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/datasets/augmentations.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"837c6a474dd26eff"}},{"code_sha256_prefix":"5c94a7e309621404","entry":"rotx","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/datasets/kitti_dataset_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/datasets/kitti_dataset_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c94a7e309621404"}},{"code_sha256_prefix":"0a19721bdaffaddd","entry":"roty","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/datasets/kitti_dataset_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/datasets/kitti_dataset_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a19721bdaffaddd"}},{"code_sha256_prefix":"e1451f5589db8939","entry":"rotz","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/datasets/kitti_dataset_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/datasets/kitti_dataset_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1451f5589db8939"}},{"code_sha256_prefix":"8f01cf597a6c5057","entry":"scale_intrinsics","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/geometry/camera_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/geometry/camera_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f01cf597a6c5057"}},{"code_sha256_prefix":"8c84d49a14bcb232","entry":"view_synthesis","repo":"TRI-ML/packnet-sfm","repo_kind":"official","path":"packnet_sfm/geometry/camera_utils.py","file_url":"https://github.com/TRI-ML/packnet-sfm/blob/HEAD/packnet_sfm/geometry/camera_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c84d49a14bcb232"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}