{"type":"ScholarlyArticle","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow (Extended Abstract)","authors":[{"name":"Zachary Teed","slug":"zachary-teed","given":"Zachary","family":"Teed","affiliation":""},{"name":"Jia Deng","slug":"jia-deng","given":"Jia","family":"Deng","affiliation":""}],"abstract":"We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes. RAFT achieves state-of-the-art performance on the KITTI and Sintel datasets. In addition, RAFT has strong cross-dataset generalization as well as high efficiency in inference time, training speed, and parameter count.","doi":"10.24963/ijcai.2021/662","url":"https://ijcai.org/proceedings/2021/662","pdf":"https://ijcai.org/proceedings/2021/0662.pdf","markdown":"https://ijcai.org/proceedings/2021/662.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/662","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":662,"pages":{"first":4839,"last":4843},"keywords":["Computer Vision: 2D and 3D Computer Vision","Computer Vision: Motion and Tracking"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}