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

Abstract

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 $256\times 512$ 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.

References in corpus (7)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• SfM-Net: Learning of Structure and Motion from Video
• Light-Weight RefineNet for Real-Time Semantic Segmentation
• SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection

Cited by in corpus (1)

• Towards Real-Time Monocular Depth Estimation for Robotics: A Survey