TY - GEN
T1 - SUNet
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
AU - Fan, Bin
AU - Dai, Yuchao
AU - He, Mingyi
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - The vast majority of modern consumer-grade cameras employ a rolling shutter mechanism, leading to image distortions if the camera moves during image acquisition. In this paper, we present a novel deep network to solve the generic rolling shutter correction problem with two consecutive frames. Our pipeline is symmetrically designed to predict the global shutter image corresponding to the intermediate time of these two frames, which is difficult for existing methods because it corresponds to a camera pose that differs most from the two frames. First, two time-symmetric dense undistortion flows are estimated by using well-established principles: pyramidal construction, warping, and cost volume processing. Then, both rolling shutter images are warped into a common global shutter one in the feature space, respectively. Finally, a symmetric consistency constraint is constructed in the image decoder to effectively aggregate the contextual cues of two rolling shutter images, thereby recovering the high-quality global shutter image. Extensive experiments with both synthetic and real data from public benchmarks demonstrate the superiority of our proposed approach over the state-of-the-art methods.
AB - The vast majority of modern consumer-grade cameras employ a rolling shutter mechanism, leading to image distortions if the camera moves during image acquisition. In this paper, we present a novel deep network to solve the generic rolling shutter correction problem with two consecutive frames. Our pipeline is symmetrically designed to predict the global shutter image corresponding to the intermediate time of these two frames, which is difficult for existing methods because it corresponds to a camera pose that differs most from the two frames. First, two time-symmetric dense undistortion flows are estimated by using well-established principles: pyramidal construction, warping, and cost volume processing. Then, both rolling shutter images are warped into a common global shutter one in the feature space, respectively. Finally, a symmetric consistency constraint is constructed in the image decoder to effectively aggregate the contextual cues of two rolling shutter images, thereby recovering the high-quality global shutter image. Extensive experiments with both synthetic and real data from public benchmarks demonstrate the superiority of our proposed approach over the state-of-the-art methods.
UR - http://www.scopus.com/inward/record.url?scp=85117859624&partnerID=8YFLogxK
U2 - 10.1109/ICCV48922.2021.00450
DO - 10.1109/ICCV48922.2021.00450
M3 - 会议稿件
AN - SCOPUS:85117859624
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 4521
EP - 4530
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 October 2021 through 17 October 2021
ER -