{"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/liteflownet-a-lightweight-convolutional","title":"LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation","arxiv_id":"1805.07036","date":"2018-05-18","proceeding":"CVPR 2018 6","authors":["Tak-Wai Hui","Xiaoou Tang","Chen Change Loy"],"abstract":"FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical\nflow estimation, requires over 160M parameters to achieve accurate flow\nestimation. In this paper we present an alternative network that outperforms\nFlowNet2 on the challenging Sintel final pass and KITTI benchmarks, while being\n30 times smaller in the model size and 1.36 times faster in the running speed.\nThis is made possible by drilling down to architectural details that might have\nbeen missed in the current frameworks: (1) We present a more effective flow\ninference approach at each pyramid level through a lightweight cascaded\nnetwork. It not only improves flow estimation accuracy through early\ncorrection, but also permits seamless incorporation of descriptor matching in\nour network. (2) We present a novel flow regularization layer to ameliorate the\nissue of outliers and vague flow boundaries by using a feature-driven local\nconvolution. (3) Our network owns an effective structure for pyramidal feature\nextraction and embraces feature warping rather than image warping as practiced\nin FlowNet2. Our code and trained models are available at\nhttps://github.com/twhui/LiteFlowNet .","url_abs":"http://arxiv.org/abs/1805.07036v1","url_pdf":"http://arxiv.org/pdf/1805.07036v1.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":"liteflownet-a-lightweight-convolutional","repo_url":"https://github.com/twhui/LiteFlowNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"liteflownet-a-lightweight-convolutional","repo_url":"https://github.com/sniklaus/pytorch-liteflownet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"liteflownet-a-lightweight-convolutional","repo_url":"https://github.com/keeper121/liteflownet-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"liteflownet-a-lightweight-convolutional","repo_url":"https://github.com/open-mmlab/mmflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/optical-flow-estimation-on-kitti-2012","task":"Optical Flow Estimation","dataset":"KITTI 2012","model":"LiteFlowNet-ft","rank_in_archive_order":11,"of":12,"metrics":{"Average End-Point Error":"1.6"},"uses_additional_data":false},{"leaderboard":"/sota/optical-flow-estimation-on-kitti-2015","task":"Optical Flow Estimation","dataset":"KITTI 2015","model":"LiteFlowNet-ft","rank_in_archive_order":15,"of":18,"metrics":{"Fl-all":"9.38"},"uses_additional_data":false},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-clean","task":"Optical Flow Estimation","dataset":"Sintel-clean","model":"LiteFlowNet-ft","rank_in_archive_order":26,"of":29,"metrics":{"Average End-Point Error":"4.54"},"uses_additional_data":false},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-final","task":"Optical Flow Estimation","dataset":"Sintel-final","model":"LiteFlowNet-ft","rank_in_archive_order":25,"of":28,"metrics":{"Average End-Point Error":"5.38"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"twhui/LiteFlowNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sniklaus/pytorch-liteflownet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"keeper121/liteflownet-tf2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"open-mmlab/mmflow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.02409"],"harvested_for_calls":[{"arxiv_id":"2104.02409","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.02409"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.02409\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"c4bc9be9e549aed1de0cb40a6d2c15cde44d92a58f3b7d2bea6b85b53476ab53","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}