Disparity Estimation

60 papers with code • 4 benchmarks • 4 datasets

The Disparity Estimation is the task of finding the pixels in the multiscopic views that correspond to the same 3D point in the scene.

Most implemented papers

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

HKBU-HPML/FADNet CVPR 2016

By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.

CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching

gallenszl/CFNet CVPR 2021

In this paper, we propose CFNet, a Cascade and Fused cost volume based network to improve the robustness of the stereo matching network.

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.

Blur aware metric depth estimation with multi-focus plenoptic cameras

comsee-research/libpleno 8 Aug 2023

A method to calibrate the inverse model is then proposed.

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.

Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching

DeepMotionAIResearch/DenseMatchingBenchmark 9 Sep 2019

However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained.

FADNet: A Fast and Accurate Network for Disparity Estimation

HKBU-HPML/FADNet 24 Mar 2020

Deep neural networks (DNNs) have achieved great success in the area of computer vision.

PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching

gallenszl/pcwnet 23 Jun 2020

First, we construct combination volumes on the upper levels of the pyramid and develop a cost volume fusion module to integrate them for initial disparity estimation.

YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection

Owen-Liuyuxuan/visualDet3D 17 Mar 2021

Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs.

SMD-Nets: Stereo Mixture Density Networks

fabiotosi92/SMD-Nets CVPR 2021

Despite stereo matching accuracy has greatly improved by deep learning in the last few years, recovering sharp boundaries and high-resolution outputs efficiently remains challenging.