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

Self-supervised monocular depth estimation methods generally suffer theocclusion fading issue due to the lack of supervision by the per pixel groundtruth. Although a post-processing method was proposed by Godard et. al. toreduce the occlusion fading, the compensated results have a severe halo effect.In this paper, we propose a novel Edge-Guided post-processing to reduce theocclusion fading issue for self-supervised monocular depth estimation. Wefurther introduce Atrous Spatial Pyramid Pooling (ASPP) into the network toreduce the computational costs and improve the inference performance. Theproposed ASPP-based network is lighter, faster, and better than currentcommonly used depth estimation networks. This light-weight network only needs8.1 million parameters and can achieve up to 40 frames per second for$256\times512$ input in the inference stage using a single nVIDIA GTX1080 GPU.The proposed network also outperforms the current state-of-the-art on the KITTIbenchmarks. The ASPP-based network and Edge-Guided post-processing producebetter results either quantitatively and qualitatively than the competitors.

Edge-Guided Occlusion Fading Reduction for a Light-Weighted Self-Supervised Monocular Depth Estimation