Stars
State-of-the-art 2D and 3D Face Analysis Project
2D AI-NR model for raw images, including dataset、training、infer.
Collection of popular and reproducible video denoising works.
PyTorch implementation of OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network (WACV 2021)
Cascaded Multi-Domain Filter for Fast Image Denoising
"Identity Enhanced Residual Image Denoising", IEEE Computer Vision and Pattern Recognition Workshop (CVPRW), 2020
Selective Residual M-Net for Real Image Denoising
A robust deformed CNN for image denoising (CAAI Transactions on Intelligence Technology,2022)
Image Denoising Using Deep Convolutional Autoencoder with Feature Pyramids
Frequency Denoising Network: Blind Noise Removal for Real Images
A curated list of resources for Low-level Vision Tasks
Designing and Training of A Dual CNN for Image Denoising (Knowledge-based Systems, 2021)
PyTorch Implementation of "Densely Connected Hierarchical Network for Image Denoising", CVPRW, NTIRE2019
LIDIA: Lightweight Learned Image Denoising with Instance Adaptation (NTIRE, 2020)
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐
[ICCV 2017] Learning Efficient Convolutional Networks through Network Slimming
Tensorflow ShuffleNet v2 implementation
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
基于卷积神经网络的数字手势识别安卓APP，识别数字手势0-10（The number gestures recognition Android APP based on convolutional neural network(CNN), which can recognize the gestures corresponding number 0 to 10）
Android TensorFlow MachineLearning Example (Building TensorFlow for Android)
Face Detection app using TF Lite C++ API on Android
在Android使用深度学习模型实现图像识别，本项目提供了多种使用方式，使用到的框架如下：Tensorflow Lite、Paddle Lite、MNN、TNN
Classify camera images locally using TensorFlow models
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥