disparity

Pytorch version of SfmLearner from Tinghui Zhou et al.

🔥🔥🔥SLAM, VIsual localization, keypoint detection, Image matching, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code

Dockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)

这是一个基于CUDA加速的快速立体匹配库，它的核心是SemiglobalMatching（SGM）算法，它不仅在时间效率上要远远优于基于CPU的常规SGM，而且占用明显更少的内存，这意味着它不仅可以在较低分辨率（百万级）图像上达到实时的帧率，且完全具备处理千万级甚至更高量级图像的能力。

Keras code of my ICRA 2018 paper "Fast Disparity Estimation using Dense Networks"

simplified struct2depth in PyTorch

Attention-based View Selection Networks for Light-field Disparity Estimation

DispNet3, FlowNet3, FlowNetH, SceneFlowNet -- in Docker

Measuring disparity with R

Tensorflow implementation of https://lmb.informatik.uni-freiburg.de/Publications/2016/MIFDB16 + pretrained weights + implementation of "Unsupervised Adaptation for Deep Stereo" (ICCV 2017)

planar fitting computation using stereo vision techniques

Official repository for "Depth estimation from 4D light field videos", IWAIT 2021

C++ implementation of PatchMatch Stereo for images

depth map computation

“Disparitybased space-variant image deblurring,” Signal Processing: Image Communication, vol. 28, no. 7, pp. 792–808, 2013.

Disparity and depth maps GUI with QT and OpenCV with support for classic image files and MPO stereo pairs

Visualize stereo_msgs/DisparityImage as RGB sensor_msgs/Image topic

Improved-PSMNet: Combining PSM, group-wise corr, dilatedResNet, segmentation to estimate accurate disparity of stereo image pairs efficiently.

Repository of data, code and supporting materials to repeat analysis performed by ODOT Research Unit documenting pedestrian injury disparities in Oregon. The standardized scoring uses an objective approach to categorizing Census tracts based on race, ethnicity, and poverty. These categories are then used to calculate population-based pedestrian injury rates for the state.

In this project, we try to implement the concept of Stereo Vision. We test the code on 3 different datasets, each of them contains 2 images of the same scenario but taken from two different camera angles. By comparing the information about a scene from 2 vantage points, we can obtain the 3D information by examining the relative positions of objects.