English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Semantic segmentation and depth completion are two challenging tasks in sceneunderstanding, and they are widely used in robotics and autonomous driving.Although several works are proposed to jointly train these two tasks using somesmall modifications, like changing the last layer, the result of one task isnot utilized to improve the performance of the other one despite that there aresome similarities between these two tasks. In this paper, we propose multi-taskgenerative adversarial networks (Multi-task GANs), which are not only competentin semantic segmentation and depth completion, but also improve the accuracy ofdepth completion through generated semantic images. In addition, we improve thedetails of generated semantic images based on CycleGAN by introducingmulti-scale spatial pooling blocks and the structural similarity reconstructionloss. Furthermore, considering the inner consistency between semantic andgeometric structures, we develop a semantic-guided smoothness loss to improvedepth completion results. Extensive experiments on Cityscapes dataset and KITTIdepth completion benchmark show that the Multi-task GANs are capable ofachieving competitive performance for both semantic segmentation and depthcompletion tasks.

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