Stereo Matching

112 papers with code • 0 benchmarks • 14 datasets

Stereo Matching is one of the core technologies in computer vision, which recovers 3D structures of real world from 2D images. It has been widely used in areas such as autonomous driving, augmented reality and robotics navigation. Given a pair of rectified stereo images, the goal of Stereo Matching is to compute the disparity for each pixel in the reference image, where disparity is defined as the horizontal displacement between a pair of corresponding pixels in the left and right images.

Source: Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching

Libraries

Use these libraries to find Stereo Matching models and implementations

Most implemented papers

HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching

google-research/google-research CVPR 2021

Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometric propagation and warping mechanisms to infer disparity hypotheses.

Pyramid Stereo Matching Network

JiaRenChang/PSMNet CVPR 2018

The spatial pyramid pooling module takes advantage of the capacity of global context information by aggregating context in different scales and locations to form a cost volume.

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

alibaba/cascade-stereo CVPR 2020

The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity.

Noise-Aware Unsupervised Deep Lidar-Stereo Fusion

XuelianCheng/LidarStereoNet CVPR 2019

In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo fusion network, which can be trained in an end-to-end manner without the need of ground truth depth maps.

MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching

cogsys-tuebingen/mobilestereonet 22 Aug 2021

Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively.

Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation

megvii-research/crestereo CVPR 2022

With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress.

Continuous 3D Label Stereo Matching using Local Expansion Moves

t-taniai/LocalExpStereo 28 Mar 2016

The local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation.

Learning for Disparity Estimation through Feature Constancy

JiaRenChang/PSMNet CVPR 2018

The second part performs matching cost calculation, matching cost aggregation and disparity calculation to estimate the initial disparity using shared features.

StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction

meteorshowers/StereoNet ECCV 2018

A first estimate of the disparity is computed in a very low resolution cost volume, then hierarchically the model re-introduces high-frequency details through a learned upsampling function that uses compact pixel-to-pixel refinement networks.

Hierarchical Discrete Distribution Decomposition for Match Density Estimation

ucbdrive/hd3 CVPR 2019

Explicit representations of the global match distributions of pixel-wise correspondences between pairs of images are desirable for uncertainty estimation and downstream applications.