Starred repositories
A Flexible and Unified Image Restoration Framework (PyTorch), including state-of-the-art image restoration model. Such as NAFNet, Restormer, MPRNet, MIMO-UNet, SCUNet, SwinIR, HINet, etc. ⭐⭐⭐⭐⭐⭐
FSA: Fusing FlashAttention within a Single Systolic Array
(CVPR 2026) Bilevel Layer-Positioning LoRA for Real Image Dehazing
MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.
This project accelerates CNN computation with the help of FPGA, for more than 50x speed-up compared with CPU.
OpenMMLab Detection Toolbox and Benchmark
HybridNets: End-to-End Perception Network
You Only Look Once for Panopitic Driving Perception.（MIR2022）
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
ECCV2020 - Practical Deep Raw Image Denoising on Mobile Devices
Physics-based Noise Modeling for Extreme Low-light Photography (CVPR 2020 Oral & TPAMI 2021)
An implementation for noise model estimation method of "A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising", CVPR 2020.
Physics-guided Noise Neural Proxy for Practical Low-light Raw Image Denoising
Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising
RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything
Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes. CVPR 2020
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
A simple cycle accurate template model for ASIC/FPGA hardware design. Including a cycle accurate FIFO design example. More designs are coming.
A simple tutorial on SystemC using NJU's DLCO experiments as examples
💫 Toolkit to help you get started with Spec-Driven Development
Repository to host and maintain SCALE-Sim code
A machine learning accelerator core designed for energy-efficient AI at the edge.
Terminal-based CPU stress and monitoring utility
General CNN_Accelerator design.卷积神经网络加速器设计。在PYNQ-Z2、ZCU102 FPGA开发板上实现了卷积池化全连接层等硬件加速计算。
校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step