# Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks

arXiv: https://arxiv.org/abs/1909.07667 · HTML: https://mlsanity.com/paper/1909.07667/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 7 of 7)

- [Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation](https://mlsanity.com/paper/2106.00985/) (2021)
- [H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry](https://mlsanity.com/paper/2104.11288/) (2021)
- [Disparity-based Stereo Image Compression with Aligned Cross-View Priors](https://mlsanity.com/paper/2212.00459/) (2022)
- [Expansion of Visual Hints for Improved Generalization in Stereo Matching](https://mlsanity.com/paper/2211.00392/) (2022)
- [Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning](https://mlsanity.com/paper/2301.13335/) (2023)
- [ViM-Disparity: Bridging the Gap of Speed, Accuracy and Memory for Disparity Map Generation](https://mlsanity.com/paper/2412.16745/) (2024)
- [CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approach](https://mlsanity.com/paper/2509.22627/) (2025)

## Abstract (arXiv)

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.