MIRNet

Tensorflow implementation of the MIRNet architecture as proposed by Learning Enriched Features for Real Image Restoration and Enhancement.

Lanuch Notebooks:

Wandb Logs: https://wandb.ai/19soumik-rakshit96/mirnet

TFLite Variant of MIRNet: https://github.com/sayakpaul/MIRNet-TFLite.

TFLite Models on Tensorflow Hub: https://tfhub.dev/sayakpaul/lite-model/mirnet-fixed/dr/1.

Tensorflow JS Variant of MIRNet: https://github.com/Rishit-dagli/MIRNet-TFJS.

Pre-trained Weights

Trained on 128x128 patches: https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing
Trained on 256x256 patches: https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing

Citation

@misc{
    2003.06792,
    Author = {Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao},
    Title = {Learning Enriched Features for Real Image Restoration and Enhancement},
    Year = {2020},
    Eprint = {arXiv:2003.06792},
}

Tensorflow implementation of MIRNet for Low-light image enhancement

Related tags

Overview

MIRNet

Pre-trained Weights

Citation

Owner

Soumik Rakshit

NeuroGen: activation optimized image synthesis for discovery neuroscience

A Blender python script for getting asset browser custom preview images for objects and collections.

Unofficial implement with paper SpeakerGAN: Speaker identification with conditional generative adversarial network

Differential fuzzing for the masses!

Real-Time-Student-Attendence-System - Real Time Student Attendence System

Unconstrained Text Detection with Box Supervisionand Dynamic Self-Training

Learning Calibrated-Guidance for Object Detection in Aerial Images

Algo-burn - Script to configure an Algorand address as a "burn" address for one or more ASA tokens

Distributed Asynchronous Hyperparameter Optimization better than HyperOpt.

Official code of the paper "Expanding Low-Density Latent Regions for Open-Set Object Detection" (CVPR 2022)

A Python script that creates subtitles of a given length from text paragraphs that can be easily imported into any Video Editing software such as FinalCut Pro for further adjustments.

Easy and Efficient Object Detector

Time-series-deep-learning - Developing Deep learning LSTM, BiLSTM models, and NeuralProphet for multi-step time-series forecasting of stock price.

[ArXiv 2021] One-Shot Generative Domain Adaptation

Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-identification

The codes and models in 'Gaze Estimation using Transformer'.

Six - a Python 2 and 3 compatibility library

Sound Source Localization for AI Grand Challenge 2021

This codebase proposes modular light python and pytorch implementations of several LiDAR Odometry methods

Official Implementation for "ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement" https://arxiv.org/abs/2104.02699