# Depth Refinement for Improved Stereo Reconstruction

arXiv: https://arxiv.org/abs/2112.08070 · HTML: https://mlsanity.com/paper/2112.08070/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 15 Dec 2021.

## Builds on (most cited first, 23 of 23)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Error bounds for approximations with deep ReLU networks](https://mlsanity.com/paper/1610.01145/) (2016)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (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)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches](https://mlsanity.com/paper/1510.05970/) (2015)
- [ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2012.05258/) (2020)
- [Why Deep Neural Networks for Function Approximation?](https://mlsanity.com/paper/1610.04161/) (2016)
- [Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching](https://mlsanity.com/paper/1708.09204/) (2017)
- [Bidirectional Attention Network for Monocular Depth Estimation](https://mlsanity.com/paper/2009.00743/) (2020)
- [RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1911.09712/) (2019)
- [Momen(e)t: Flavor the Moments in Learning to Classify Shapes](https://mlsanity.com/paper/1812.07431/) (2018)

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

- [GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views](https://mlsanity.com/paper/2404.01810/) (2024)

## Abstract (arXiv)

Depth estimation is a cornerstone of a vast number of applications requiring 3D assessment of the environment, such as robotics, augmented reality, and autonomous driving to name a few. One prominent technique for depth estimation is stereo matching which has several advantages: it is considered more accessible than other depth-sensing technologies, can produce dense depth estimates in real-time, and has benefited greatly from the advances of deep learning in recent years. However, current techniques for depth estimation from stereoscopic images still suffer from a built-in drawback. To reconstruct depth, a stereo matching algorithm first estimates the disparity map between the left and right images before applying a geometric triangulation. A simple analysis reveals that the depth error is quadratically proportional to the object's distance. Therefore, constant disparity errors are translated to large depth errors for objects far from the camera. To mitigate this quadratic relation, we propose a simple but effective method that uses a refinement network for depth estimation. We show analytical and empirical results suggesting that the proposed learning procedure reduces this quadratic relation. We evaluate the proposed refinement procedure on well-known benchmarks and datasets, like Sceneflow and KITTI datasets, and demonstrate significant improvements in the depth accuracy metric.