Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency

Abstract

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.

References in corpus (8)

• Conditional Generative Adversarial Nets
• Deep Subdomain Adaptation Network for Image Classification
• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• A Survey on Multi-Task Learning
• Monocular Depth Estimation Based On Deep Learning: An Overview
• Confidence Propagation through CNNs for Guided Sparse Depth Regression
• Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency