{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/propagating-confidences-through-cnns-for","title":"Propagating Confidences through CNNs for Sparse Data Regression","arxiv_id":"1805.11913","date":"2018-05-30","proceeding":null,"authors":["Abdelrahman Eldesokey","Michael Felsberg","Fahad Shahbaz Khan"],"abstract":"In most computer vision applications, convolutional neural networks (CNNs)\noperate on dense image data generated by ordinary cameras. Designing CNNs for\nsparse and irregularly spaced input data is still an open problem with numerous\napplications in autonomous driving, robotics, and surveillance. To tackle this\nchallenging problem, we introduce an algebraically-constrained convolution\nlayer for CNNs with sparse input and demonstrate its capabilities for the scene\ndepth completion task. We propose novel strategies for determining the\nconfidence from the convolution operation and propagating it to consecutive\nlayers. Furthermore, we propose an objective function that simultaneously\nminimizes the data error while maximizing the output confidence. Comprehensive\nexperiments are performed on the KITTI depth benchmark and the results clearly\ndemonstrate that the proposed approach achieves superior performance while\nrequiring three times fewer parameters than the state-of-the-art methods.\nMoreover, our approach produces a continuous pixel-wise confidence map enabling\ninformation fusion, state inference, and decision support.","url_abs":"http://arxiv.org/abs/1805.11913v3","url_pdf":"http://arxiv.org/pdf/1805.11913v3.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":"propagating-confidences-through-cnns-for","repo_url":"https://github.com/abdo-eldesokey/nconv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"depth-completion","task_name":"Depth Completion"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.11913","atlas_url":"https://app.syntology.ai/?focus=1805.11913","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1805.11913"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1805.11913\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1805.11913"},"call":"get_concepts_for_paper(arxiv_id=\"1805.11913\")"}],"by_repo":[{"repo":"abdo-eldesokey/nconv","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bcd45673f1b3930b1a58b597021ab708017528a4638dfb462c2a7511e7aa7a7e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}