dingkeyan93 / Dists
Licence: mit
IQA: Deep Image Structure and Texture Similarity Metric
Stars: ✭ 101
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Dists
Auxpack
A dashboard for monitoring Webpack build stats.
Stars: ✭ 86 (-14.85%)
Mutual labels: optimization
Go Perfbook
Thoughts on Go performance optimization
Stars: ✭ 9,597 (+9401.98%)
Mutual labels: optimization
Qreverse
A small study in hardware accelerated AoS reversal
Stars: ✭ 97 (-3.96%)
Mutual labels: optimization
Beautiful React Redux
Redux 🚀, Redux 🤘, Redux 🔥 - and the magic optimization
Stars: ✭ 87 (-13.86%)
Mutual labels: optimization
Jplusone
Tool for automatic detection and asserting "N+1 SELECT problem" occurences in JPA based Spring Boot Java applications and finding origin of JPA issued SQL statements in general
Stars: ✭ 91 (-9.9%)
Mutual labels: optimization
Rinsim
RinSim is a logistics simulator written in Java. RinSim supports (de)centralized algorithms for dynamic pickup-and-delivery problems (PDP). The simulator is developed at the imec-DistriNet group at the dept. of Computer Science, KU Leuven, Belgium.
Stars: ✭ 91 (-9.9%)
Mutual labels: optimization
Monkeys
A strongly-typed genetic programming framework for Python
Stars: ✭ 98 (-2.97%)
Mutual labels: optimization
Nlp Journey
Documents, papers and codes related to Natural Language Processing, including Topic Model, Word Embedding, Named Entity Recognition, Text Classificatin, Text Generation, Text Similarity, Machine Translation),etc. All codes are implemented intensorflow 2.0.
Stars: ✭ 1,290 (+1177.23%)
Mutual labels: similarity
Proximaloperators.jl
Proximal operators for nonsmooth optimization in Julia
Stars: ✭ 92 (-8.91%)
Mutual labels: optimization
Csso Rails
CSS Optimizer(csso) ruby wrapper for Rails Asset pipeline
Stars: ✭ 86 (-14.85%)
Mutual labels: optimization
Assetkit
🎨 Modern 2D/3D - Importer • Exporter • Util - Library, also called (AssetIO)
Stars: ✭ 97 (-3.96%)
Mutual labels: texture
Training Material
A collection of code examples as well as presentations for training purposes
Stars: ✭ 85 (-15.84%)
Mutual labels: optimization
Deep Learning Drizzle
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
Stars: ✭ 9,717 (+9520.79%)
Mutual labels: optimization
Advisor
Open-source implementation of Google Vizier for hyper parameters tuning
Stars: ✭ 1,359 (+1245.54%)
Mutual labels: optimization
Webpack Conditional Loader
C conditionals directive for JavaScript
Stars: ✭ 93 (-7.92%)
Mutual labels: optimization
Deep Image Structure and Texture Similarity (DISTS) Metric
This is the repository of paper Image Quality Assessment: Unifying Structure and Texture Similarity.
Highlights:
- A full-reference IQA model correlated well with human perception of image quality.
- It is robust to texture variance (e.g., evaluating the images generated by GANs) and mild geometric transformations (e.g., evaluating the image pairs that are not strictly point-by-point aligned).
- It can be employed as an objective function in various optimization problems (see optimization comparison).
Three implementation versions:
- Pytorch
DISTS_pt.py
(recommend) - Tensorflow
DISTS_tf.py
- Matlab
DISTS.m
.
====== Pytorch ======
Installation:
pip install dists-pytorch
Requirements:
- Python>=3.6
- Pytorch>=1.0
Usage:
from DISTS_pytorch import DISTS
D = DISTS()
# calculate DISTS between X, Y (a batch of RGB images, data range: 0~1)
# X: (N,C,H,W)
# Y: (N,C,H,W)
dists_value = D(X, Y)
# set 'require_grad=True, batch_average=True' to get a scalar value as loss.
dists_loss = D(X, Y, require_grad=True, batch_average=True)
dists_loss.backward()
or
git clone https://github.com/dingkeyan93/DISTS
cd DISTS_pytorch
python DISTS_pt.py --ref <ref_path> --dist <dist_path>
====== Tensorflow ======
Requirements:
- Python>=3.6
- Tensorflow>=1.15
Usage:
git clone https://github.com/dingkeyan93/DISTS
cd DISTS_tensorflow
python DISTS_tf.py --ref <ref_path> --dist <dist_path>
====== Matlab ======
Requirements:
- Matlab>=2019b
Usage:
git clone https://github.com/dingkeyan93/DISTS
run demo.m
help DISTS
Citation
@article{ding2020iqa,
title={Image Quality Assessment: Unifying Structure and Texture Similarity},
author={Ding, Keyan and Ma, Kede and Wang, Shiqi and Simoncelli, Eero P.},
journal = {CoRR},
volume = {abs/2004.07728},
year={2020},
url = {https://arxiv.org/abs/2004.07728}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].