Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks

TL;DR

This paper introduces a novel unsupervised binocular depth estimation method using a Progressive Fusion Network with a cyclic architecture and adversarial training, achieving competitive results on major datasets.

Contribution

The paper proposes a new multi-scale fusion network architecture and a cyclic training strategy for unsupervised binocular depth estimation, enhancing depth prediction without ground truth annotations.

Findings

Effective depth estimation on KITTI, Cityscapes, ApolloScape datasets.

Competitive performance compared to existing unsupervised methods.

Cycle-based training improves depth prediction accuracy.

Abstract

Recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance. However, they require costly ground truth annotations during training. To cope with this issue, in this paper we present a novel unsupervised deep learning approach for predicting depth maps. We introduce a new network architecture, named Progressive Fusion Network (PFN), that is specifically designed for binocular stereo depth estimation. This network is based on a multi-scale refinement strategy that combines the information provided by both stereo views. In addition, we propose to stack twice this network in order to form a cycle. This cycle approach can be interpreted as a form of data-augmentation since, at training time, the network learns both from the training set images (in the forward half-cycle) but also from the synthesized images (in the backward half-cycle). The architecture is jointly trained with adversarial learning. Extensive experiments on the publicly available datasets KITTI, Cityscapes and ApolloScape demonstrate the effectiveness of the proposed model which is competitive with other unsupervised deep learning methods for depth prediction.