arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06591cs.CV
收藏

基于多视点自监督的单幅图像室外逆绘制

Outdoor inverse rendering from a single image using multiview self-supervision

University of York(约克大学)

Ye Yu, William A. P. Smith

摘要:

在本文中,我们将展示如何执行场景级逆渲染恢复形状,反射率和照明从一个单一的,不受控制的图像使用一个完全卷积神经网络。该网络以RGB图像作为输入,回归阴影,阴影和法线映射,从中我们推断出最小二乘最佳球谐照明系数。我们的网络使用大型不受控制的多视图和时间推移图像集合进行训练,而没有地面实况。通过引入可区分的渲染器,我们的网络可以从自我监督中学习。由于问题是不适定的,我们引入了额外的监督。我们的主要见解是执行离线多视图立体(MVS)的图像包含丰富的照明变化。从MVS姿态和深度图,我们可以在重叠视图之间进行交叉投影,从而可以使用Siamese训练来确保对光度不变量的一致估计。MVS深度还为法线映射估计提供直接粗略监督。我们相信这是第一次尝试使用MVS监督学习逆渲染。此外,我们还学习了一个统计的自然光照先验。我们评估性能的逆渲染,正常的地图估计和内在的图像分解基准。

英文摘要:

In this paper we show how to perform scene-level inverse rendering to recover shape, reflectance and lighting from a single, uncontrolled image using a fully convolutional neural network. The network takes an RGB image as input, regresses albedo, shadow and normal maps from which we infer least squares optimal spherical harmonic lighting coefficients. Our network is trained using large uncontrolled multiview and timelapse image collections without ground truth. By incorporating a differentiable renderer, our network can learn from self-supervision. Since the problem is ill-posed we introduce additional supervision. Our key insight is to perform offline multiview stereo (MVS) on images containing rich illumination variation. From the MVS pose and depth maps, we can cross project between overlapping views such that Siamese training can be used to ensure consistent estimation of photometric invariants. MVS depth also provides direct coarse supervision for normal map estimation. We believe this is the first attempt to use MVS supervision for learning inverse rendering. In addition, we learn a statistical natural illumination prior. We evaluate performance on inverse rendering, normal map estimation and intrinsic image decomposition benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑