# Stereo Computation for a Single Mixture Image

arXiv: https://arxiv.org/abs/1808.08690 · HTML: https://mlsanity.com/paper/1808.08690/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 6 of 6)

- [ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring](https://mlsanity.com/paper/2103.04260/) (2021)
- [Deep Two-View Structure-from-Motion Revisited](https://mlsanity.com/paper/2104.00556/) (2021)
- [Vicinity Vision Transformer](https://mlsanity.com/paper/2206.10552/) (2022)
- [Blind Image Decomposition](https://mlsanity.com/paper/2108.11364/) (2021)
- [Self-Supervised Visibility Learning for Novel View Synthesis](https://mlsanity.com/paper/2103.15407/) (2021)
- [Deep Laparoscopic Stereo Matching with Transformers](https://mlsanity.com/paper/2207.12152/) (2022)

## Abstract (arXiv)

This paper proposes an original problem of stereo computation from a single mixture image-- a challenging problem that had not been researched before. The goal is to separate (ie, unmix) a single mixture image into two constitute image layers, such that the two layers form a left-right stereo image pair, from which a valid disparity map can be recovered. This is a severely illposed problem, from one input image one effectively aims to recover three (ie, left image, right image and a disparity map). In this work we give a novel deep-learning based solution, by jointly solving the two subtasks of image layer separation as well as stereo matching. Training our deep net is a simple task, as it does not need to have disparity maps. Extensive experiments demonstrate the efficacy of our method.