VALSE 论文速览 第125期：雾天场景光流估计算法UCDA-Flow

论文题目：Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow

作者列表：

周寒宇 (华中科技大学)，昌毅 (华中科技大学)，闫问鼎 (华为国际有限公司)，颜露新 (华中科技大学)

B站观看网址：

https://www.bilibili.com/video/BV19k4y1A7ki/

论文摘要：

Optical flow has achieved great success under clean scenes, but suffers from restricted performance under foggy scenes. To bridge the clean-to-foggy domain gap, the existing methods typically adopt the domain adaptation to transfer the motion knowledge from clean to synthetic foggy domain. However, these methods unexpectedly neglect the synthetic-to-real domain gap, and thus are erroneous when applied to real-world scenes. To handle the practical optical flow under real foggy scenes, in this work, we propose a novel unsupervised cumulative domain adaptation optical flow (UCDA-Flow) framework: depth-association motion adaptation and correlation-alignment motion adaptation. Specifically, we discover that depth is a key ingredient to influence the optical flow: the deeper depth, the inferior optical flow, which motivates us to design a depth-association motion adaptation module to bridge the clean-to-foggy domain gap. Moreover, we figure out that the cost volume correlation shares similar distribution of the synthetic and real foggy images, which enlightens us to devise a correlation-alignment motion adaptation module to distill motion knowledge of the synthetic foggy domain to the real foggy domain. Note that synthetic fog is designed as the intermediate domain. Under this unified framework, the proposed cumulative adaptation progressively transfers knowledge from clean scenes to real foggy scenes. Extensive experiments have been performed to verify the superiority of the proposed method.

论文信息：

[1] Hanyu Zhou, Yi Chang*, Wending Yan, Luxin Yan. Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow. In CVPR 2023, pages 9569-9578.

论文链接：

[https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Unsupervised_Cumulative_Domain_Adaptation_for_Foggy_Scene_Optical_Flow_CVPR_2023_paper.pdf]

代码链接：

[https://github.com/hyzhouboy/UCDA-Flow]

视频讲者简介：

周寒宇，华中科技大学在读博士。在CVPR/ AAAI等国际高水平会议发表多篇论文，博士期间主要研究方向是复杂场景运动估计和知识迁移。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：杨帅 (南洋理工大学)