# Unsupervised learning of depth and motion

arXiv: https://arxiv.org/abs/1312.3429 · HTML: https://mlsanity.com/paper/1312.3429/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2013.

## Built on by (most cited first, 1 of 1)

- [Dilated Fully Convolutional Neural Network for Depth Estimation from a Single Image](https://mlsanity.com/paper/2103.07570/) (2021)

## Abstract (arXiv)

We present a model for the joint estimation of disparity and motion. The model is based on learning about the interrelations between images from multiple cameras, multiple frames in a video, or the combination of both. We show that learning depth and motion cues, as well as their combinations, from data is possible within a single type of architecture and a single type of learning algorithm, by using biologically inspired "complex cell" like units, which encode correlations between the pixels across image pairs. Our experimental results show that the learning of depth and motion makes it possible to achieve state-of-the-art performance in 3-D activity analysis, and to outperform existing hand-engineered 3-D motion features by a very large margin.