ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2019, Vol. 56 ›› Issue (2): 385-393.doi: 10.7544/issn1000-1239.2019.20170897

• 图形图像 • 上一篇    下一篇

单帧图像下的环境光遮蔽估计

郭雨潇1,陈雷霆1,2,董悦3   

  1. 1(电子科技大学计算机科学与工程学院 成都 611731); 2(电子科技大学广东电子工程信息研究院 广东东莞 523808); 3(微软亚洲研究院 北京 100080) (yuxiao.guo@outlook.com)
  • 出版日期: 2019-02-01
  • 基金资助: 
    广东省应用型科技研发专项资金项目(2015B010131002)

Inferring Ambient Occlusion from a Single Image

Guo Yuxiao1, Chen Leiting1,2, Dong Yue3   

  1. 1(School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731); 2(Institute of Electronic and Information Engineering in Guangdong, University of Electronic Science and Technology of China, Dongguan, Guangdong 523808); 3(Microsoft Research Asia, Beijing 100080)
  • Online: 2019-02-01

摘要: 环境光遮蔽(ambient occlusion)被广泛用于近似计算低频全局光照、消除间接光照和阴影等计算机图形学和视觉应用中.已有算法直接通过场景的3维几何,或不同光照下的多幅图像计算每个点的环境光遮蔽,存在着对光照和输入图像数量要求高等问题.针对以上不足,提出了一种基于单张图像的环境光遮蔽估计算法.算法利用一个在大量仿真图像数据集上训练的卷积神经网络,直接从自然光照条件下场景的单张图像中恢复每个点的环境光遮蔽.提出并比较了3种不同的神经网络结构设计,实验分析验证了端到端的设计方案可以获得最佳的结果.和已有的环境光遮蔽算法方法比较,所提出的方法不仅计算速度快,而且在数值和视觉上具有更好的结果.

关键词: 环境光遮蔽, 本征图像, 自然光照, 卷积神经网络, 自动编码器

Abstract: Ambient occlusion has been widely used in many graphics and vision tasks for approxi-mating low frequency global illumination, removing inter-reflection, and inferring scene geometry. Existing methods need either scene geometry or scene appearances under different lightings to compute the ambient occlusion of the scene, which limits the application of these methods in many real applications. In this paper, we present a new method for computing the ambient occlusion from a single image taken under unknown natural lighting. Our method needn’t any scene geometry or illumination information. To this end, we utilize a convolutional neural network (CNN), trained on a large amount of synthetic data, to directly recovery the pre-pixel ambient occlusion. We propose three network structures for ambient occlusion estimation, a cascade one and a parallel one that are based on previous CNN solution for intrinsic images, as well as an end-to-end neural network. We analyze their performance and demonstrate that comparing with parallel and cascade designs, the end-to-end design could achieve the best performance. We also valid the efficiency and effectiveness of our method on both synthetic and real images. It is not only faster, but also more accurate than previous methods.

Key words: ambient occlusion, intrinsic image, natural illumination, convolutional neural network, autoencoder

中图分类号: