Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency
This work addresses the problem of improving depth completion accuracy for robotics and autonomous driving by leveraging semantic information, which is an incremental improvement over existing joint training methods.
This paper proposes Multi-task GANs to jointly train semantic segmentation and depth completion, where generated semantic images improve depth completion accuracy. The method also enhances semantic image details using multi-scale spatial pooling and structural similarity reconstruction loss, and improves depth completion with a semantic-guided smoothness loss.
Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving. Although several works are proposed to jointly train these two tasks using some small modifications, like changing the last layer, the result of one task is not utilized to improve the performance of the other one despite that there are some similarities between these two tasks. In this paper, we propose multi-task generative adversarial networks (Multi-task GANs), which are not only competent in semantic segmentation and depth completion, but also improve the accuracy of depth completion through generated semantic images. In addition, we improve the details of generated semantic images based on CycleGAN by introducing multi-scale spatial pooling blocks and the structural similarity reconstruction loss. Furthermore, considering the inner consistency between semantic and geometric structures, we develop a semantic-guided smoothness loss to improve depth completion results. Extensive experiments on Cityscapes dataset and KITTI depth completion benchmark show that the Multi-task GANs are capable of achieving competitive performance for both semantic segmentation and depth completion tasks.