{"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/proflow-learning-to-predict-optical-flow","title":"ProFlow: Learning to Predict Optical Flow","arxiv_id":"1806.00800","date":"2018-06-03","proceeding":null,"authors":["Daniel Maurer","Andrés Bruhn"],"abstract":"Temporal coherence is a valuable source of information in the context of\noptical flow estimation. However, finding a suitable motion model to leverage\nthis information is a non-trivial task. In this paper we propose an\nunsupervised online learning approach based on a convolutional neural network\n(CNN) that estimates such a motion model individually for each frame. By\nrelating forward and backward motion these learned models not only allow to\ninfer valuable motion information based on the backward flow, they also help to\nimprove the performance at occlusions, where a reliable prediction is\nparticularly useful. Moreover, our learned models are spatially variant and\nhence allow to estimate non-rigid motion per construction. This, in turns,\nallows to overcome the major limitation of recent rigidity-based approaches\nthat seek to improve the estimation by incorporating additional stereo/SfM\nconstraints. Experiments demonstrate the usefulness of our new approach. They\nnot only show a consistent improvement of up to 27% for all major benchmarks\n(KITTI 2012, KITTI 2015, MPI Sintel) compared to a baseline without prediction,\nthey also show top results for the MPI Sintel benchmark -- the one of the three\nbenchmarks that contains the largest amount of non-rigid motion.","url_abs":"http://arxiv.org/abs/1806.00800v1","url_pdf":"http://arxiv.org/pdf/1806.00800v1.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":[],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/optical-flow-estimation-on-sintel-clean","task":"Optical Flow Estimation","dataset":"Sintel-clean","model":"ProFlow+ft","rank_in_archive_order":17,"of":29,"metrics":{"Average End-Point Error":"2.82"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.00800","atlas_url":"https://app.syntology.ai/?focus=1806.00800","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":"1806.00800"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1806.00800\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1806.00800"},"call":"get_concepts_for_paper(arxiv_id=\"1806.00800\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2f13b2a3d7d68b3c8486aa2c93c3848d739ec41cb077ad3bf32b2ee7b641b40a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}