# Image-Coupled Volume Propagation for Stereo Matching

arXiv: https://arxiv.org/abs/2301.00695 · HTML: https://mlsanity.com/paper/2301.00695/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 30 Dec 2022.

## Builds on (most cited first, 29 of 29)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [Why gradient clipping accelerates training: A theoretical justification for adaptivity](https://mlsanity.com/paper/1905.11881/) (2019)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches](https://mlsanity.com/paper/1510.05970/) (2015)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [Hierarchical Deep Stereo Matching on High-resolution Images](https://mlsanity.com/paper/1912.06704/) (2019)
- [HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching](https://mlsanity.com/paper/2007.12140/) (2020)
- [A Survey on Deep Learning Techniques for Stereo-based Depth Estimation](https://mlsanity.com/paper/2006.02535/) (2020)
- [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://mlsanity.com/paper/1807.08865/) (2018)
- [Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching](https://mlsanity.com/paper/1708.09204/) (2017)
- [PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching](https://mlsanity.com/paper/2006.12797/) (2020)
- [DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow](https://mlsanity.com/paper/2204.00330/) (2022)
- [ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems](https://mlsanity.com/paper/1807.06009/) (2018)
- [Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks](https://mlsanity.com/paper/2112.01011/) (2021)
- [AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching](https://mlsanity.com/paper/2004.04627/) (2020)
- [StereoDRNet: Dilated Residual Stereo Net](https://mlsanity.com/paper/1904.02251/) (2019)
- [ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images](https://mlsanity.com/paper/2103.07798/) (2021)

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

- [Playing to Vision Foundation Model's Strengths in Stereo Matching](https://mlsanity.com/paper/2404.06261/) (2024)

## Abstract (arXiv)

Several leading methods on public benchmarks for depth-from-stereo rely on memory-demanding 4D cost volumes and computationally intensive 3D convolutions for feature matching. We suggest a new way to process the 4D cost volume where we merge two different concepts in one deeply integrated framework to achieve a symbiotic relationship. A feature matching part is responsible for identifying matching pixels pairs along the baseline while a concurrent image volume part is inspired by depth-from-mono CNNs. However, instead of predicting depth directly from image features, it provides additional context to resolve ambiguities during pixel matching. More technically, the processing of the 4D cost volume is separated into a 2D propagation and a 3D propagation part. Starting from feature maps of the left image, the 2D propagation assists the 3D propagation part of the cost volume at different layers by adding visual features to the geometric context. By combining both parts, we can safely reduce the scale of 3D convolution layers in the matching part without sacrificing accuracy. Experiments demonstrate that our end-to-end trained CNN is ranked 2nd on KITTI2012 and ETH3D benchmarks while being significantly faster than the 1st-ranked method. Furthermore, we notice that the coupling of image and matching-volume improves fine-scale details as demonstrated by our qualitative analysis.