# Dual CNN Models for Unsupervised Monocular Depth Estimation

arXiv: https://arxiv.org/abs/1804.06324 · HTML: https://mlsanity.com/paper/1804.06324/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2018.

## Built on by (most cited first, 8 of 8)

- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification](https://mlsanity.com/paper/2107.11979/) (2021)
- [Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep Learning](https://mlsanity.com/paper/2103.10179/) (2021)
- [Detecting Environmental Violations with Satellite Imagery in Near Real Time: Land Application under the Clean Water Act](https://mlsanity.com/paper/2208.08919/) (2022)
- [Semantic Map Injected GAN Training for Image-to-Image Translation](https://mlsanity.com/paper/2112.01845/) (2021)
- [Moment Centralization based Gradient Descent Optimizers for Convolutional Neural Networks](https://mlsanity.com/paper/2207.09066/) (2022)
- [EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training](https://mlsanity.com/paper/2506.16017/) (2025)

## Abstract (arXiv)

The unsupervised depth estimation is the recent trend by utilizing the binocular stereo images to get rid of depth map ground truth. In unsupervised depth computation, the disparity images are generated by training the CNN with an image reconstruction loss. In this paper, a dual CNN based model is presented for unsupervised depth estimation with 6 losses (DNM6) with individual CNN for each view to generate the corresponding disparity map. The proposed dual CNN model is also extended with 12 losses (DNM12) by utilizing the cross disparities. The presented DNM6 and DNM12 models are experimented over KITTI driving and Cityscapes urban database and compared with the recent state-of-the-art result of unsupervised depth estimation. The code is available at: https://github.com/ishmav16/Dual-CNN-Models-for-Unsupervised-Monocular-Depth-Estimation.