Online Overexposed Pixels Hallucination in Videos with Adaptive Reference Frame Selection
Abstract
Low dynamic range (LDR) cameras cannot deal with wide dynamic range inputs, frequently leading to local overexposure issues. We present a learning-based system to reduce these artifacts without resorting to complex acquisition mechanisms like alternating exposures or costly processing that are typical of high dynamic range (HDR) imaging. We propose a transformer-based deep neural network (DNN) to infer the missing HDR details. In an ablation study, we show the importance of using a multiscale DNN and train it with the proper cost function to achieve state-of-the-art quality. To aid the reconstruction of the overexposed areas, our DNN takes a reference frame from the past as an additional input. This leverages the commonly occurring temporal instabilities of autoexposure to our advantage: since well-exposed details in the current frame may be overexposed in the future, we use reinforcement learning to train a reference frame selection DNN that decides whether to adopt the current frame as a future reference. Without resorting to alternating exposures, we obtain therefore a causal, HDR hallucination algorithm with potential application in common video acquisition settings. Our demo video can be found at https://drive.google.com/file/d/1-r12BKImLOYCLUoPzdebnMyNjJ4Rk360/view
Cite
@article{arxiv.2308.15462,
title = {Online Overexposed Pixels Hallucination in Videos with Adaptive Reference Frame Selection},
author = {Yazhou Xing and Amrita Mazumdar and Anjul Patney and Chao Liu and Hongxu Yin and Qifeng Chen and Jan Kautz and Iuri Frosio},
journal= {arXiv preprint arXiv:2308.15462},
year = {2023}
}
Comments
The demo video can be found at https://drive.google.com/file/d/1-r12BKImLOYCLUoPzdebnMyNjJ4Rk360/view