NTIRE 2019 Challenge on Video Deblurring and Super-Resolution: Dataset and Study

By Seungjun Nah, Sungyong Baik, Seokil Hong, Gyeongsik Moon, Sanghyun Son, Radu Timofte, Kyoung Mu Lee. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019

613 citations recorded by the source corpus.

This paper introduces a novel large dataset for video deblurring, video super-resolution and studies the state-of-the-art as emerged from the NTIRE 2019 video restoration challenges. The video deblurring and video super-resolution challenges are each the first challenge of its kind, with 4 competitions, hundreds of participants and tens of proposed solutions. Our newly collected REalistic and Diverse Scenes dataset (REDS) was employed by the challenges. In our study, we compare the solutions from the challenges to a set of representative methods from the literature and evaluate them on our proposed REDS dataset. We find that the NTIRE 2019 challenges push the state-of-the-art in video deblurring and super-resolution, reaching compelling performance on our newly proposed REDS dataset.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6274a77e319c648a75468545f77cb270c3362594

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

A Deep Journey into Super-resolution (2019, background): “Recently, an extensive challenge was organized for real-image super-resolution in CVPR’19 to promote development on this crucial research problem [110], [111].”
Stripformer: Strip Transformer for Fast Image Deblurring (2022, methodology): “To further leverage the pre-training data, we utilize the REDS dataset [44] (with 24,000 images) as the pre-training data and then fine-tune the model on the GoPro training set.”
BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond (2020, methodology): “BI degradation BD degradation Params (M) Runtime (ms) REDS4 [23] Vimeo-90K-T [33] Vid4 [21] UDM10 [34] Vimeo-90K-T [33] Vid4 [21] Bicubic - 26.”
HINet: Half Instance Normalization Network for Image Restoration (2021, methodology): “3× speedup on REDS [30] and GoPro [31] datasets.”
BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment (2021, methodology): “All results are calculated on Y-channel except REDS4 [21] (RGB-channel).”
Deep Image Deblurring: A Survey (2022, methodology): “The first group transfers the feature maps from the last step to the current network to obtain finer deblurred frames (Hyun Kim et al. 2017; Nah et al. 2019).”
VRT: A Video Restoration Transformer (2022, methodology): “First, we generate low-resolution images by the MATLAB imresize function ( i . e ., bicubic degradation) and train the model on REDS [60].”
EDVR: Video Restoration With Enhanced Deformable Convolutional Networks (2019, background): “The challenge releases a valuable benchmark, known as REalistic and Diverse Scenes dataset (REDS) [26], for the aforementioned tasks.”
Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms (2020, background): “Recently, several synthetic datasets for learning image deblurring have been proposed [31, 30, 32, 39, 51].”