当前位置: X-MOL 学术IEEE Trans. Image Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Designing an Illumination-Aware Network for Deep Image Relighting
IEEE Transactions on Image Processing ( IF 10.8 ) Pub Date : 8-10-2022 , DOI: 10.1109/tip.2022.3195366
Zuo-Liang Zhu 1 , Zhen Li 1 , Rui-Xun Zhang 2 , Chun-Le Guo 1 , Ming-Ming Cheng 1
Affiliation  

Lighting is a determining factor in photography that affects the style, expression of emotion, and even quality of images. Creating or finding satisfying lighting conditions, in reality, is laborious and time-consuming, so it is of great value to develop a technology to manipulate illumination in an image as post-processing. Although previous works have explored techniques based on the physical viewpoint for relighting images, extensive supervisions and prior knowledge are necessary to generate reasonable images, restricting the generalization ability of these works. In contrast, we take the viewpoint of image-to-image translation and implicitly merge ideas of the conventional physical viewpoint. In this paper, we present an Illumination-Aware Network (IAN) which follows the guidance from hierarchical sampling to progressively relight a scene from a single image with high efficiency. In addition, an Illumination-Aware Residual Block (IARB) is designed to approximate the physical rendering process and to extract precise descriptors of light sources for further manipulations. We also introduce a depth-guided geometry encoder for acquiring valuable geometry- and structure-related representations once the depth information is available. Experimental results show that our proposed method produces better quantitative and qualitative relighting results than previous state-of-the-art methods. The code and models are publicly available on https://github.com/NK-CS-ZZL/IAN.

中文翻译:


设计用于深度图像重新照明的照明感知网络



光线是摄影中的决定性因素,影响着风格、情感的表达,甚至图像的质量。实际上,创建或找到令人满意的照明条件是费力且耗时的,因此开发一种在图像后处理中操纵图像照明的技术具有重要价值。尽管以前的作品已经探索了基于物理视点重新照亮图像的技术,但需要广泛的监督和先验知识来生成合理的图像,限制了这些作品的泛化能力。相比之下,我们采取图像到图像转换的观点,并隐含地融合了传统物理观点的思想。在本文中,我们提出了一种照明感知网络(IAN),它遵循分层采样的指导,以高效率逐步从单个图像重新照亮场景。此外,照明感知残差块(IARB)旨在近似物理渲染过程并提取光源的精确描述符以进行进一步操作。我们还引入了深度引导几何编码器,一旦深度信息可用,即可获取有价值的几何和结构相关表示。实验结果表明,我们提出的方法比以前最先进的方法产生更好的定量和定性重新照明结果。代码和模型可在 https://github.com/NK-CS-ZZL/IAN 上公开获取。
更新日期:2024-08-28
down
wechat
bug