{"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/fdflownet-fast-optical-flow-estimation-using","title":"FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network","arxiv_id":"2006.12263","date":"2020-06-22","proceeding":null,"authors":["Lingtong Kong","Jie Yang"],"abstract":"Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this work, we present a lightweight yet effective model for real-time optical flow estimation, termed FDFlowNet (fast deep flownet). We achieve better or similar accuracy on the challenging KITTI and Sintel benchmarks while being about 2 times faster than PWC-Net. This is achieved by a carefully-designed structure and newly proposed components. We first introduce an U-shape network for constructing multi-scale feature which benefits upper levels with global receptive field compared with pyramid network. In each scale, a partial fully connected structure with dilated convolution is proposed for flow estimation that obtains a good balance among speed, accuracy and number of parameters compared with sequential connected and dense connected structures. Experiments demonstrate that our model achieves state-of-the-art performance while being fast and lightweight.","url_abs":"https://arxiv.org/abs/2006.12263v1","url_pdf":"https://arxiv.org/pdf/2006.12263v1.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":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/optical-flow-estimation-on-kitti-2012","task":"Optical Flow Estimation","dataset":"KITTI 2012","model":"FDFlowNet-ft","rank_in_archive_order":9,"of":12,"metrics":{"Average End-Point Error":"1.5"},"uses_additional_data":false},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-clean","task":"Optical Flow Estimation","dataset":"Sintel-clean","model":"FDFlowNet-ft","rank_in_archive_order":22,"of":29,"metrics":{"Average End-Point Error":"3.71"},"uses_additional_data":false},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-final","task":"Optical Flow Estimation","dataset":"Sintel-final","model":"FDFlowNet-ft","rank_in_archive_order":23,"of":28,"metrics":{"Average End-Point Error":"5.11"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}