CVNov 26, 2019

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

arXiv:1911.11705v13 citations
Originality Incremental advance
AI Analysis

This work addresses occlusion fading for self-supervised monocular depth estimation, which is an incremental improvement in computer vision for applications like autonomous driving.

The paper tackles occlusion fading in self-supervised monocular depth estimation by proposing an Edge-Guided post-processing method and integrating Atrous Spatial Pyramid Pooling (ASPP) into the network, resulting in a lighter network with 8.1 million parameters achieving up to 40 FPS and outperforming state-of-the-art on KITTI benchmarks.

Self-supervised monocular depth estimation methods generally suffer the occlusion fading issue due to the lack of supervision by the per pixel ground truth. Although a post-processing method was proposed by Godard et. al. to reduce the occlusion fading, the compensated results have a severe halo effect. In this paper, we propose a novel Edge-Guided post-processing to reduce the occlusion fading issue for self-supervised monocular depth estimation. We further introduce Atrous Spatial Pyramid Pooling (ASPP) into the network to reduce the computational costs and improve the inference performance. The proposed ASPP-based network is lighter, faster, and better than current commonly used depth estimation networks. This light-weight network only needs 8.1 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 KITTI benchmarks. The ASPP-based network and Edge-Guided post-processing produce better results either quantitatively and qualitatively than the competitors.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes