# Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision

arXiv: https://arxiv.org/abs/2209.05082 · HTML: https://mlsanity.com/paper/2209.05082/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 71 references that are in the map.
- First posted on arXiv 12 Sep 2022.

## Builds on (most cited first, 30 of 35)

- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users](https://mlsanity.com/paper/2007.06823/) (2020)
- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [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)
- [HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching](https://mlsanity.com/paper/2007.12140/) (2020)
- [PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds](https://mlsanity.com/paper/1901.01060/) (2019)
- [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)
- [Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era](https://mlsanity.com/paper/1906.06543/) (2019)
- [Intel RealSense Stereoscopic Depth Cameras](https://mlsanity.com/paper/1705.05548/) (2017)
- [MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching](https://mlsanity.com/paper/2108.09770/) (2021)
- [Anytime Stereo Image Depth Estimation on Mobile Devices](https://mlsanity.com/paper/1810.11408/) (2018)
- [Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift](https://mlsanity.com/paper/1908.01098/) (2019)
- [On Information Plane Analyses of Neural Network Classifiers -- A Review](https://mlsanity.com/paper/2003.09671/) (2020)
- [ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems](https://mlsanity.com/paper/1807.06009/) (2018)
- [On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation](https://mlsanity.com/paper/2001.08049/) (2020)
- [Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning](https://mlsanity.com/paper/1701.00165/) (2016)
- [The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning](https://mlsanity.com/paper/1811.12535/) (2018)
- [Left-Right Comparative Recurrent Model for Stereo Matching](https://mlsanity.com/paper/1804.00796/) (2018)
- [Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures](https://mlsanity.com/paper/1903.04939/) (2019)
- [Separable Convolutions for Optimizing 3D Stereo Networks](https://mlsanity.com/paper/2108.10216/) (2021)

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

- [Active-Passive SimStereo -- Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods](https://mlsanity.com/paper/2209.08305/) (2022)

## Abstract (arXiv)

A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision. Active vision systems enable more accurate estimations of dense disparity compared to passive stereo. However, subpixel-accurate disparity estimation remains an open problem that has received little attention. In this paper, we propose a new learning strategy to train neural networks to estimate high-quality subpixel disparity maps for semi-dense active stereo vision. The key insight is that neural networks can double their accuracy if they are able to jointly learn how to refine the disparity map while invalidating the pixels where there is insufficient information to correct the disparity estimate. Our approach is based on Bayesian modeling where validated and invalidated pixels are defined by their stochastic properties, allowing the model to learn how to choose by itself which pixels are worth its attention. Using active stereo datasets such as Active-Passive SimStereo, we demonstrate that the proposed method outperforms the current state-of-the-art active stereo models. We also demonstrate that the proposed approach compares favorably with state-of-the-art passive stereo models on the Middlebury dataset.