NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results

This paper reviews the first challenge on high-dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2021. This manuscript focuses on the newly introduced dataset, the proposed methods and their results. The challenge aims at estimating a HDR image from one or multiple respective low-dynamic range (LDR) observations, which might suffer from under-or over-exposed regions and different sources of noise. The challenge is composed by two tracks: In Track 1 only a single LDR image is provided as input, whereas in Track 2 three differently-exposed LDR images with inter-frame motion are available. In both tracks, the ultimate goal is to achieve the best objective HDR reconstruction in terms of PSNR with respect to a ground-truth image, evaluated both directly and with a canonical tonemapping operation.

[1]  Chao Dong,et al.  Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Chen Change Loy,et al.  EDVR: Video Restoration With Enhanced Deformable Convolutional Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[3]  Radu Timofte,et al.  NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[4]  Ing Ren Tsang,et al.  Single image HDR reconstruction using a CNN with masked features and perceptual loss , 2020, ACM Trans. Graph..

[5]  Yu Qiao,et al.  HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Luc Van Gool,et al.  Seven Ways to Improve Example-Based Single Image Super Resolution , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Jitendra Malik,et al.  Recovering high dynamic range radiance maps from photographs , 1997, SIGGRAPH '08.

[8]  Rizwan Ali Naqvi,et al.  Learning Medical Image Denoising with Deep Dynamic Residual Attention Network , 2020, Mathematics.

[9]  Soo Ye Kim,et al.  JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video , 2020, AAAI.

[10]  Gabriel Eilertsen,et al.  HDR image reconstruction from a single exposure using deep CNNs , 2017, ACM Trans. Graph..

[11]  Radu Timofte,et al.  NTIRE 2021 Challenge on Video Super-Resolution , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  A AkhilK.,et al.  Single image HDR synthesis using a Densely Connected Dilated ConvNet , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[13]  Yi Yang,et al.  Gated Channel Transformation for Visual Recognition , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Frédo Durand,et al.  Noise-optimal capture for high dynamic range photography , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Radu Timofte,et al.  NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[16]  Haoqiang Fan,et al.  ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[17]  Yun Fu,et al.  Residual Dense Network for Image Super-Resolution , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Ling Shao,et al.  NTIRE 2021 NonHomogeneous Dehazing Challenge Report , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Shree K. Nayar,et al.  Optical Splitting Trees for High-Precision Monocular Imaging , 2007, IEEE Computer Graphics and Applications.

[20]  Pablo Navarrete Michelini,et al.  Single-Image HDR Reconstruction with Task-specific Network based on Channel Adaptive RDN , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[21]  Jenq-Neng Hwang,et al.  NTIRE 2021 Multi-modal Aerial View Object Classification Challenge , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[22]  Rizwan Ali Naqvi,et al.  A Two-stage Deep Network for High Dynamic Range Image Reconstruction , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[23]  Yung-Yu Chuang,et al.  Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Yi Li,et al.  Deformable Convolutional Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  Radu Timofte,et al.  NTIRE 2021 Depth Guided Image Relighting Challenge , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[26]  Ravi Ramamoorthi,et al.  Deep HDR Video from Sequences with Alternating Exposures , 2019, Comput. Graph. Forum.

[27]  Fahad Shahbaz Khan,et al.  NTIRE 2021 Challenge for Defocus Deblurring Using Dual-pixel Images: Methods and Results , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[28]  Jan Kautz,et al.  Exposure Fusion , 2007, 15th Pacific Conference on Computer Graphics and Applications (PG'07).

[29]  Jan Kautz,et al.  PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[30]  R. Venkatesh Babu,et al.  Towards Practical and Efficient High-Resolution HDR Deghosting with CNN , 2020, ECCV.

[31]  Radu Timofte,et al.  NTIRE 2021 Challenge on Perceptual Image Quality Assessment , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[32]  Pradeep Sen,et al.  A versatile HDR video production system , 2011, ACM Trans. Graph..

[33]  Radu Timofte,et al.  NTIRE 2021 Challenge on Image Deblurring , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[34]  Yanning Zhang,et al.  Attention-Guided Network for Ghost-Free High Dynamic Range Imaging , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Syed Waqas Zamir,et al.  Learning Enriched Features for Real Image Restoration and Enhancement , 2020, ECCV.

[36]  Eli Shechtman,et al.  Robust patch-based hdr reconstruction of dynamic scenes , 2012, ACM Trans. Graph..

[37]  Chi-Keung Tang,et al.  End-to-End Deep HDR Imaging with Large Foreground Motions , 2017, ArXiv.

[38]  Jiashi Feng,et al.  Coordinate Attention for Efficient Mobile Network Design , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  B. H. Pawan Prasad,et al.  Deep Multi-Stage Learning for HDR With Large Object Motions , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[40]  Kun Gao,et al.  NTIRE 2021 Learning the Super-Resolution Space Challenge , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[41]  Harald Brendel,et al.  Creating cinematic wide gamut HDR-video for the evaluation of tone mapping operators and HDR-displays , 2014, Electronic Imaging.

[42]  Ravi Ramamoorthi,et al.  Deep high dynamic range imaging of dynamic scenes , 2017, ACM Trans. Graph..