Image relighting aims to recalibrate the illumination setting in an image. In this paper, we propose a deep learning-based method called multi-modal bifurcated network (MBNet) for depth guided image relighting. That is, given an image and the corresponding depth maps, a new image with the given illuminant angle and color temperature is generated by our network. This model extracts the image and the depth features by the bifurcated network in the encoder. To use the two features effectively, we adopt the dynamic dilated pyramid modules in the decoder. Moreover, to increase the variety of training data, we propose a novel data process pipeline to increase the number of the training data. Experiments conducted on the VIDIT dataset show that the proposed solution obtains the \textbf{1}$^{st}$ place in terms of SSIM and PMS in the NTIRE 2021 Depth Guide One-to-one Relighting Challenge.

翻译：图像光照旨在重新校正图像中的照明设置。 在本文中, 我们提出一种深层次的学习方法, 叫做多式双向网络( MBNet), 用于深度引导图像光化。 也就是说, 给图像和相应的深度地图, 由我们的网络生成一个带有给定光度角度和色温的新图像。 这个模型提取了在编码器中双向网络的图像和深度特征。 为了有效地使用这两个特征, 我们在解码器中采用了动态扩张的金字塔模块。 此外, 为了增加培训数据的多样性, 我们提议了一个新的数据流程管道, 以增加培训数据的数量。 在VIDIT数据集上进行的实验显示, 拟议的解决方案获得了 SSIM 和 PMS 在 2021 深度指南一对一的“ 亮亮亮挑战” 中的位置 。