서강대학교

초록/요약

Deep convolutional neural networks (CNNs) have made significant advances in the inverse tone mapping technique, which generates a high dynamic range (HDR) image from a single low dynamic range (LDR) image that has lost information in over- and under-exposed regions. In particular, the method of generating multiple exposure LDR images from a single LDR image and subsequently merging them into an HDR image enables flexible dynamic range expansion. However, existing methods require an additional network for each exposure value to be changed or a process of recursively inferring the network that changes by a specific exposure value. Therefore, the number of parameters increases significantly due to the use of additional networks, and an error accumulation problem arises due to recursive inference. To solve this problem, we propose a novel network architecture that can control arbitrary exposure values without adding networks or applying recursive inference. The training method of the auxiliary classifier-generative adversarial network structure is employed to generate the image conditioned on the specified exposure. The proposed network uses a newly designed spatially-adaptive normalization to address the limitation of existing methods that cannot sufficiently restore image detail due to the spatially equivariant nature of the convolution. Experimental results show that the proposed method outperforms state-of-the-art methods for various datasets.