Results 31 to 40 of about 4,876 (175)
Recurrence-in-Recurrence Networks for Video Deblurring
Proceedings of the British Machine Vision Conference 2021, 2021 State-of-the-art video deblurring methods often adopt recurrent neural networks to model the temporal dependency between the frames. While the hidden states play key role in delivering information to the next frame, abrupt motion blur tend to weaken the relevance in the neighbor frames.
Park, Joonkyu +2 more
openaire +2 more sources
, 2016 Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on aligning nearby frames.
Su, Shuochen +5 more
openaire +2 more sources
Deblurring by Realistic Blurring
, 2020 Existing deep learning methods for image deblurring typically train models using pairs of sharp images and their blurred counterparts. However, synthetically blurring images do not necessarily model the genuine blurring process in real-world scenarios ...
Li, Hongdong +6 more
core +1 more source
Video Deblurring with Deconvolution and Aggregation Networks
SSRN Electronic Journal, 2022 In contrast to single-image deblurring, video deblurring has the advantage that neighbor frames can be utilized to deblur a target frame. However, existing video deblurring algorithms often fail to properly employ the neighbor frames, resulting in sub-optimal performance. In this paper, we propose a deconvolution and aggregation network (DAN) for video
Choi, Giyong, Park, HyunWook
openaire +2 more sources
Simultaneous Stereo Video Deblurring and Scene Flow Estimation
, 2017 Videos for outdoor scene often show unpleasant blur effects due to the large relative motion between the camera and the dynamic objects and large depth variations. Existing works typically focus monocular video deblurring.
Dai, Yuchao +3 more
core +1 more source
Simulated Artifacts and Data Augmentation for Real-World Video Motion Deblurring
IEEE AccessThis paper proposes a data augmentation method that simulates artifacts specific to real-world videos as a preprocessing step for applying a deep learning-based video deblurring method to real-world videos.
Sota Moriyama, Kaito Kira, Koichi Ichige
doaj +1 more source
Spatio-Temporal Deformable Attention Network for Video Deblurring
, 2022 The key success factor of the video deblurring methods is to compensate for the blurry pixels of the mid-frame with the sharp pixels of the adjacent video frames. Therefore, mainstream methods align the adjacent frames based on the estimated optical flows and fuse the alignment frames for restoration.
Huicong Zhang, Haozhe Xie, Hongxun Yao
openaire +2 more sources
Event-guided Deblurring of Unknown Exposure Time Videos
, 2022 Motion deblurring is a highly ill-posed problem due to the loss of motion information in the blur degradation process. Since event cameras can capture apparent motion with a high temporal resolution, several attempts have explored the potential of events for guiding deblurring.
Taewoo Kim +3 more
openaire +2 more sources
Learning Blind Motion Deblurring
, 2017 As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime. However, taking a quick shot frequently yields a blurry result due to unwanted camera shake during recording ...
Hirsch, Michael +3 more
core +1 more source
Blur More To Deblur Better: Multi-Blur2Deblur For Efficient Video Deblurring
, 2020 9 pages, 7 ...
Park, Dongwon +2 more
openaire +2 more sources