HDR-GAN: HDR Image Reconstruction From Multi-Exposed LDR Images With Large Motions

Niu, Yuzhen; Wu, Jianbin; Liu, Wenxi; Guo, Wenzhong; Lau, Rynson W. H.

doi:10.1109/tip.2021.3064433

Cited by 98 publications

(69 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Datasets: We use the dynamic training and testing datasets provided by Kalantari and Ramamoorthi [7] which includes Wu [8] Prabhakar [21] AHDR [13] Ours HDRGAN [15] ADNet [16] Prabhakar [18] Sen [30] Kalantari [7] GT Fig. 6.…”

Section: Resultsmentioning

confidence: 99%

“…To keep it consistent with training, we restrict the number of input frames to three with EVs of -2.00, 0.00, +2.00. Metrics: We include three different objective metrics in our quantitative evaluation, reproducing the same benchmark setup as recent publications [8], [13], [15]. First, we compute the PSNR-L, which is a fidelity metric computed directly on the linear HDR estimations.…”

Section: Resultsmentioning

confidence: 99%

“…More recently, the state of the art in HDR imaging has been pushed to new highs. [15] propose the first GAN-based approach to HDR reconstruction which is able to synthesize missing details in areas with disocclusions. Liu et al [16] introduce a method which uses deformable convolutions as an alignment mechanism instead of optical flow and was the winning submission to the 2021 NTIRE HDR Challenge [17].…”

Section: Related Workmentioning

confidence: 99%

“…Wu [8] Prabhakar [21] AHDR [13] Ours HDRGAN [15] ADNet [16] Prabhakar [18] Sen [30] Kalantari [7] GT Fig. 7.…”

Section: B Performance Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging

Catley-Chandar,

Tanay,

Vandroux

et al. 2022

Preprint

View full text Add to dashboard Cite

High dynamic range (HDR) imaging is of fundamental importance in modern digital photography pipelines and used to produce a high-quality photograph with well exposed regions despite varying illumination across the image. This is typically achieved by merging multiple low dynamic range (LDR) images taken at different exposures. However, over-exposed regions and misalignment errors due to poorly compensated motion result in artefacts such as ghosting. In this paper, we present a new HDR imaging technique that specifically models alignment and exposure uncertainties to produce high quality HDR results. We introduce a strategy that learns to jointly align and assess the alignment and exposure reliability using an HDR-aware, uncertainty-driven attention map that robustly merges the frames into a single high quality HDR image. Further, we introduce a progressive, multi-stage image fusion approach that can flexibly merge any number of LDR images in a permutation-invariant manner. Experimental results show our method can produce better quality HDR images with up to 0.8dB PSNR improvement to the state-of-the-art, and subjective improvements in terms of better detail, colours, and fewer artefacts.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Wu [8] Prabhakar [21] AHDR [13] Ours HDRGAN [15] ADNet [16] Prabhakar [18] Sen [30] Kalantari [7] GT Fig. 7.…”

Section: B Performance Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging

Catley-Chandar,

Tanay,

Vandroux

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Traditional single image contrast enhancement techniques include Histogram equalization (HE) [12,13], Retinex [12,13], and High dynamic range(HDR) [14,15]. HE methods enhance the low-light images by adjusting the contrast of the image, but it inevitably brings undesirable illumination.…”

Section: Introductionmentioning

confidence: 99%

Single Low-Light Ghost-Free Image Enhancement via Deep Retinex Model

Liu¹,

Lv²,

Wang³

et al. 2021

KSII TIIS

View full text Add to dashboard Cite

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from lowresolution. To reduce the noise of the enhanced image and improve the image quality, a superresolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

show abstract

Selective TransHDR: Transformer-Based Selective HDR Imaging Using Ghost Region Mask

Song

Park

Kong

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

HDR-GAN: HDR Image Reconstruction From Multi-Exposed LDR Images With Large Motions

Cited by 98 publications

References 36 publications

FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging

FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging

Single Low-Light Ghost-Free Image Enhancement via Deep Retinex Model

Selective TransHDR: Transformer-Based Selective HDR Imaging Using Ghost Region Mask

Contact Info

Product

Resources

About