# Digging Into Self-Supervised Monocular Depth Estimation

arXiv: https://arxiv.org/abs/1806.01260 · HTML: https://mlsanity.com/paper/1806.01260/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2018.

## Built on by (most cited first, 2 of 2)

- [Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction](https://mlsanity.com/paper/2201.12170/) (2022)
- [OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarios](https://mlsanity.com/paper/2307.10934/) (2023)

## Abstract (arXiv)

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods. Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark.