TY - GEN
T1 - High Dynamic Range Imaging Using Deep Image Priors
AU - Jagatap, Gauri
AU - Hegde, Chinmay
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - Traditionally, dynamic range enhancement for images has involved a combination of contrast improvement (via gamma correction or histogram equalization) and a denoising operation to reduce the effects of photon noise. More recently, modulo-imaging methods have been introduced for high dynamic range photography to significantly expand dynamic range at the sensing stage itself. The transformation function for both of these problems is highly non-linear, and the image reconstruction procedure is typically non-convex and ill-posed. A popular recent approach is to regularize the above inverse problem via a neural network prior (such as a trained autoencoder), but this requires extensive training over a dataset with thousands of paired regular/HDR image data samples.In this paper, we introduce a new approach for HDR image reconstruction using neural priors that require no training data. Specifically, we employ deep image priors, which have been successfully used for imaging problems such as denoising, super-resolution, inpainting and compressive sensing with promising performance gains over conventional regularization techniques. In this paper, we consider two different approaches to high dynamic range (HDR) imaging - gamma encoding and modulo encoding - and propose a combination of deep image prior and total variation (TV) regularization for reconstructing low-light images. We demonstrate the significant improvement achieved by both of these approaches as compared to traditional dynamic range enhancement techniques.
AB - Traditionally, dynamic range enhancement for images has involved a combination of contrast improvement (via gamma correction or histogram equalization) and a denoising operation to reduce the effects of photon noise. More recently, modulo-imaging methods have been introduced for high dynamic range photography to significantly expand dynamic range at the sensing stage itself. The transformation function for both of these problems is highly non-linear, and the image reconstruction procedure is typically non-convex and ill-posed. A popular recent approach is to regularize the above inverse problem via a neural network prior (such as a trained autoencoder), but this requires extensive training over a dataset with thousands of paired regular/HDR image data samples.In this paper, we introduce a new approach for HDR image reconstruction using neural priors that require no training data. Specifically, we employ deep image priors, which have been successfully used for imaging problems such as denoising, super-resolution, inpainting and compressive sensing with promising performance gains over conventional regularization techniques. In this paper, we consider two different approaches to high dynamic range (HDR) imaging - gamma encoding and modulo encoding - and propose a combination of deep image prior and total variation (TV) regularization for reconstructing low-light images. We demonstrate the significant improvement achieved by both of these approaches as compared to traditional dynamic range enhancement techniques.
KW - Deep image prior
KW - HDR imaging
KW - convolutional networks
KW - inverse imaging
KW - low-light enhancement
KW - modulo camera
KW - untrained neural networks
UR - http://www.scopus.com/inward/record.url?scp=85089241412&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089241412&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9054218
DO - 10.1109/ICASSP40776.2020.9054218
M3 - Conference contribution
AN - SCOPUS:85089241412
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 9289
EP - 9293
BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Y2 - 4 May 2020 through 8 May 2020
ER -