# The Sampling-Gaussian for stereo matching

arXiv: https://arxiv.org/abs/2410.06527 · HTML: https://mlsanity.com/paper/2410.06527/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [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)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [RAFT-3D: Scene Flow using Rigid-Motion Embeddings](https://mlsanity.com/paper/2012.00726/) (2020)
- [MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching](https://mlsanity.com/paper/2108.09770/) (2021)
- [Numerical Coordinate Regression with Convolutional Neural Networks](https://mlsanity.com/paper/1801.07372/) (2018)
- [IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching](https://mlsanity.com/paper/2409.00638/) (2024)
- [Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching](https://mlsanity.com/paper/1909.03751/) (2019)
- [Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation](https://mlsanity.com/paper/2108.05773/) (2021)
- [Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks](https://mlsanity.com/paper/2112.01011/) (2021)
- [PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching](https://mlsanity.com/paper/2103.07094/) (2021)
- [Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching](https://mlsanity.com/paper/2307.16509/) (2023)
- [Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching](https://mlsanity.com/paper/1806.01677/) (2018)
- [Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching](https://mlsanity.com/paper/2306.15612/) (2023)
- [Localization with Sampling-Argmax](https://mlsanity.com/paper/2110.08825/) (2021)
- [Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices](https://mlsanity.com/paper/2405.11809/) (2024)

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

- [MARCO: Navigating the Unseen Space of Semantic Correspondence](https://mlsanity.com/paper/2604.18267/) (2026)

## Abstract (arXiv)

The soft-argmax operation is widely adopted in neural network-based stereo matching methods to enable differentiable regression of disparity. However, network trained with soft-argmax is prone to being multimodal due to absence of explicit constraint to the shape of the probability distribution. Previous methods leverages Laplacian distribution and cross-entropy for training but failed to effectively improve the accuracy and even compromises the efficiency of the network. In this paper, we conduct a detailed analysis of the previous distribution-based methods and propose a novel supervision method for stereo matching, Sampling-Gaussian. We sample from the Gaussian distribution for supervision. Moreover, we interpret the training as minimizing the distance in vector space and propose a combined loss of L1 loss and cosine similarity loss. Additionally, we leveraged bilinear interpolation to upsample the cost volume. Our method can be directly applied to any soft-argmax-based stereo matching method without a reduction in efficiency. We have conducted comprehensive experiments to demonstrate the superior performance of our Sampling-Gaussian. The experimental results prove that we have achieved better accuracy on five baseline methods and two datasets. Our method is easy to implement, and the code is available online.