# DISCO: Depth Inference from Stereo using Context

## TL;DR

DISCO is a novel deep learning model for stereo depth inference that preserves spatial details and exploits multi-scale context, achieving state-of-the-art results on real-world images, including a new synthetic dataset.

## Contribution

The paper introduces a carefully designed architecture that maintains spatial information and captures multi-scale context, along with a new synthetic dataset for real-life stereo images.

## Key findings

- DISCO outperforms existing methods on benchmarks.
- The synthetic dataset improves real-world stereo matching.
- The architecture effectively preserves low-level details.

## Abstract

Recent deep learning based approaches have outperformed classical stereo matching methods. However, current deep learning based end-to-end stereo matching methods adopt a generic encoder-decoder style network with skip connections. To limit computational requirement, many networks perform excessive down sampling, which results in significant loss of useful low-level information. Additionally, many network designs do not exploit the rich multi-scale contextual information. In this work, we address these aforementioned problems by carefully designing the network architecture to preserve required spatial information throughout the network, while at the same time achieve large effective receptive field to extract multiscale contextual information. For the first time, we create a synthetic disparity dataset reflecting real life images captured using a smartphone; this enables us to obtain state-of-the-art results on common real life images. The proposed model DISCO is pre-trained on the synthetic Scene Flow dataset and evaluated on popular benchmarks and our in-house dataset of challenging real life images. The proposed model outperforms existing state-of-the-art methods in terms of quality as well as quantitative metrics.