ICBAIE 2020

Welcome Prof. Rongrong Ji, ​from School of Informatics, Xiamen University, China to be Keynote Speaker!

Title: Semi-Supervised Adversarial Monocular Depth Estimation

Abstract: In this research, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available. To achieve a high regression accuracy, the state-of-the-art estimation methods rely on CNNs trained with a large number of image-depth pairs, which are prohibitively costly or even infeasible to acquire. Aiming to break the curse of such expensive data collections, we propose a semi-supervised adversarial learning framework that only utilizes a small number of image-depth pairs in conjunction with a large number of easily-available monocular images to achieve high performance. In particular, we use one generator to regress the depth and two discriminators to evaluate the predicted depth, i.e., one inspects the image-depth pair while the other inspects the depth channel alone. These two discriminators provide their feedbacks to the generator as the loss to generate more realistic and accurate depth predictions. Experiments show that the proposed approach can improve most state-of-the-art models on the NYUD v2 dataset by effectively.