BSRSC
RS correction
A project for developing and evaluating a method to remove rolling shutter effects from video frames using adaptive warping and machine learning
[CVPR 2022] Learning Adaptive Warping for Real-World Rolling Shutter Correction
27 stars
3 watching
2 forks
Language: Python
last commit: 6 months ago Related projects:
Repository | Description | Stars |
---|---|---|
zzh-tech/rscd | Develops tools and techniques for correcting rolling shutter distortion in images and videos from dynamic scenes | 88 |
zzh-tech/dual-reversed-rs | Reverses rolling shutter distortion in images to produce undistorted global shutter sequences | 52 |
lightchaserx/neural-global-shutter | Reverses rolling shutter distortion in camera footage | 12 |
gitcvfb/rssr | Software tool to invert rolling shutter camera images and generate high framerate global shutter video | 35 |
irvlab/unrolling | A Python project that uses IMU data to correct rolling shutter distortion in single-view images | 18 |
rimchang/rsblur | This repository provides an implementation of an image deblurring method using realistic blur synthesis. | 82 |
lhaippp/homography-mixtures | Removes rolling shutter effects from images by estimating homographies between consecutive frames | 8 |
gitcvfb/sunet | Removes distortion from images taken with rolling shutter cameras | 22 |
cszn/srmd | Develops a single convolutional network to handle various image degradations with improved scalability and efficiency | 426 |
eyalnaor/videorollingshutter | An implementation of video rolling shutter correction using internal and external constraints. | 8 |
gitcvfb/cvr | Reconstructs high-quality video frames from two adjacent rolling shutter camera frames | 31 |
kristapsdz/openrsync | An implementation of rsync with a subset of its command-line arguments | 402 |
zzh-tech/bit | Develops a deep learning-based method for deblurring images and videos from motion blur | 222 |
kjvarga/rr-to-rspec-converter | Converts RR code to RSpec syntax for mocking and stubbing | 1 |
cszn/ircnn | This project trains deep CNN denoisers to improve image restoration tasks such as deblurring and demosaicking through model-based optimization methods. | 600 |