# End-to-End Training of Hybrid CNN-CRF Models for Stereo

arXiv: https://arxiv.org/abs/1611.10229 · HTML: https://mlsanity.com/paper/1611.10229/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2016.

## Built on by (most cited first, 10 of 10)

- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry](https://mlsanity.com/paper/2104.09877/) (2021)
- [Neural Markov Random Field for Stereo Matching](https://mlsanity.com/paper/2403.11193/) (2024)
- [Energy-Based Generative Cooperative Saliency Prediction](https://mlsanity.com/paper/2106.13389/) (2021)
- [FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion](https://mlsanity.com/paper/2209.06525/) (2022)
- [Deep Dependency Networks for Multi-Label Classification](https://mlsanity.com/paper/2302.00633/) (2023)
- [Computer vision tasks for intelligent aerospace missions: An overview](https://mlsanity.com/paper/2407.06513/) (2024)
- [Relational Neural Markov Random Fields](https://mlsanity.com/paper/2110.09647/) (2021)
- [Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification](https://mlsanity.com/paper/2404.11667/) (2024)
- [SAda-Net: A Self-Supervised Adaptive Stereo Estimation CNN For Remote Sensing Image Data](https://mlsanity.com/paper/2410.13500/) (2024)

## Abstract (arXiv)

We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs compute expressive features for matching and distinctive color edges, which in turn are used to compute the unary and binary costs of the CRF. For inference, we apply a recently proposed highly parallel dual block descent algorithm which only needs a small fixed number of iterations to compute a high-quality approximate minimizer. As the main contribution of the paper, we propose a theoretically sound method based on the structured output support vector machine (SSVM) to train the hybrid CNN+CRF model on large-scale data end-to-end. Our trained models perform very well despite the fact that we are using shallow CNNs and do not apply any kind of post-processing to the final output of the CRF. We evaluate our combined models on challenging stereo benchmarks such as Middlebury 2014 and Kitti 2015 and also investigate the performance of each individual component.