{"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-sparse-to-dense-self","title":"Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera","arxiv_id":"1807.00275","date":"2018-07-01","proceeding":null,"authors":["Fangchang Ma","Guilherme Venturelli Cavalheiro","Sertac Karaman"],"abstract":"Depth completion, the technique of estimating a dense depth image from sparse\ndepth measurements, has a variety of applications in robotics and autonomous\ndriving. However, depth completion faces 3 main challenges: the irregularly\nspaced pattern in the sparse depth input, the difficulty in handling multiple\nsensor modalities (when color images are available), as well as the lack of\ndense, pixel-level ground truth depth labels. In this work, we address all\nthese challenges. Specifically, we develop a deep regression model to learn a\ndirect mapping from sparse depth (and color images) to dense depth. We also\npropose a self-supervised training framework that requires only sequences of\ncolor and sparse depth images, without the need for dense depth labels. Our\nexperiments demonstrate that our network, when trained with semi-dense\nannotations, attains state-of-the- art accuracy and is the winning approach on\nthe KITTI depth completion benchmark at the time of submission. Furthermore,\nthe self-supervised framework outperforms a number of existing solutions\ntrained with semi- dense annotations.","url_abs":"http://arxiv.org/abs/1807.00275v2","url_pdf":"http://arxiv.org/pdf/1807.00275v2.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-sparse-to-dense-self","repo_url":"https://github.com/fangchangma/self-supervised-depth-completion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-supervised-sparse-to-dense-self","repo_url":"https://github.com/LakshmiTeja17/NNFL-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"depth-completion","task_name":"Depth Completion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-completion-on-void","task":"Depth Completion","dataset":"VOID","model":"SS-S2D","rank_in_archive_order":6,"of":6,"metrics":{"MAE":"178.85","RMSE":"243.84","iMAE":"80.12","iRMSE":"107.69"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.00275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.00275"}},"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/LakshmiTeja17/NNFL-Project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fangchangma/self-supervised-depth-completion","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"131f184af3ac28d1","entry":"conv_bn_relu","repo":"fangchangma/self-supervised-depth-completion","repo_kind":"official","path":"model.py","file_url":"https://github.com/fangchangma/self-supervised-depth-completion/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"131f184af3ac28d1"}},{"code_sha256_prefix":"b6547951e9e79482","entry":"convt_bn_relu","repo":"fangchangma/self-supervised-depth-completion","repo_kind":"official","path":"model.py","file_url":"https://github.com/fangchangma/self-supervised-depth-completion/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6547951e9e79482"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}