{"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/conditional-prior-networks-for-optical-flow","title":"Conditional Prior Networks for Optical Flow","arxiv_id":"1807.10378","date":"2018-07-26","proceeding":"ECCV 2018 9","authors":["Yanchao Yang","Stefano Soatto"],"abstract":"Classical computation of optical flow involves generic priors (regularizers)\nthat capture rudimentary statistics of images, but not long-range correlations\nor semantics. On the other hand, fully supervised methods learn the regularity\nin the annotated data, without explicit regularization and with the risk of\noverfitting. We seek to learn richer priors on the set of possible flows that\nare statistically compatible with an image. Once the prior is learned in a\nsupervised fashion, one can easily learn the full map to infer optical flow\ndirectly from two or more images, without any need for (additional)\nsupervision. We introduce a novel architecture, called Conditional Prior\nNetwork (CPN), and show how to train it to yield a conditional prior. When used\nin conjunction with a simple optical flow architecture, the CPN beats all\nvariational methods and all unsupervised learning-based ones using the same\ndata term. It performs comparably to fully supervised ones, that however are\nfine-tuned to a particular dataset. Our method, on the other hand, performs\nwell even when transferred between datasets.","url_abs":"http://arxiv.org/abs/1807.10378v1","url_pdf":"http://arxiv.org/pdf/1807.10378v1.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":"conditional-prior-networks-for-optical-flow","repo_url":"https://github.com/YanchaoYang/Conditional-Prior-Networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.10378","atlas_url":"https://app.syntology.ai/?focus=1807.10378","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":"1807.10378"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1807.10378\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1807.10378"},"call":"get_concepts_for_paper(arxiv_id=\"1807.10378\")"}],"by_repo":[{"repo":"YanchaoYang/Conditional-Prior-Networks","kind":"official","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":"afb8ffa8feb7c11f1b1a4988252b579e6e79b0c7b251a99376c0b817d3ff36c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}