Self-Supervised Monocular Depth Estimation with Internal Feature Fusion

Abstract

Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial and semantic representations from images. Therefore, it is natural to exploit semantic segmentation networks for depth estimation. In this work, based on a well-developed semantic segmentation network HRNet, we propose a novel depth estimation network DIFFNet, which can make use of semantic information in down and upsampling procedures. By applying feature fusion and an attention mechanism, our proposed method outperforms the state-of-the-art monocular depth estimation methods on the KITTI benchmark. Our method also demonstrates greater potential on higher resolution training data. We propose an additional extended evaluation strategy by establishing a test set of challenging cases, empirically derived from the standard benchmark.

Accepted at BMVC2021

References in corpus (4)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes
• Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues

Cited by in corpus (4)

• Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinement
• Image Patch-Matching with Graph-Based Learning in Street Scenes
• On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation
• Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation