Look-Ahead Training with Learned Reflectance Loss for Single-Image SVBRDF Estimation
Siggraph Asia 2022



In this paper, we propose a novel optimization-based method to estimate the reflectance properties of a near planar surface from a single input image. Specifically, we perform test-time optimization by directly updating the parameters of a neural network to minimize the test error. Since single image SVBRDF estimation is a highly ill-posed problem, such an optimization is prone to overfitting. Our main contribution is to address this problem by introducing a training mechanism that takes the test-time optimization into account. Specifically, we train our network by minimizing the training loss after one or more gradient updates with the test loss. By training the network in this manner, we ensure that the network does not overfit to the input image during the test-time optimization process. Additionally, we propose a learned reflectance loss to augment the typically used rendering loss during the test-time optimization. We do so by using an auxiliary network that estimates pseudo ground truth reflectance parameters and train it in combination with the main network. Our approach is able to converge with a small number of iterations of the test-time optimization and produces better results compared to the state-of-the-art methods.

Fast Forward Video


                author = {Zhou, Xilong and Khademi Kalantari, Nima}, 
                title = {Look-Ahead Training with Learned Reflectance Loss for Single-Image SVBRDF Estimation},
                journal = {ACM Transactions on Graphics}, 
                volume = {41}, 
                number = {6}, 
                year = {2022}, 
                month = {12}, 
                doi = {10.1145/3550454.3555495} 


We thank the Siggraph Asia 2022 reviewers for their constructive comments. The website template was borrowed from Michael Gharbi.