Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
-
Updated
Jul 27, 2020 - Python
Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
[T-RO 2022] Official Implementation for "LiCaS3: A Simple LiDAR–Camera Self-Supervised Synchronization Method," in IEEE Transactions on Robotics, doi: 10.1109/TRO.2022.3167455.
Comparing different similarity functions for reconstruction of image on CycleGAN. (https://tandon-a.github.io/CycleGAN_ssim/) Training cycleGAN with different loss functions to improve visual quality of produced images
The re-implementation of ICCV 2017 DeepFuse paper idea
A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM.
An Explaniable Deep-Learning Project: finish visual defect detection and localization task under unsupervised learning setting
Unsupervised Image-to-Image Translation by Matching the Characteristics of Images
Generating fantasy planets with GANs.
This Repository Implements Deep NMF using Autoencoders, to deblur the images.
This project is inspired by the art work titled "Out of All Things One, and Out of One All Things" created by Petros Vrellis.
Add a description, image, and links to the ssim-loss topic page so that developers can more easily learn about it.
To associate your repository with the ssim-loss topic, visit your repo's landing page and select "manage topics."