ppsdk's repositories
dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
UVM-Net
U-shaped Vision Mamba for Single Image Dehazing
DocShadow-SD7K
[ICCV 2023] A large-scale high-resolution dataset satisfies all important data features about document shadow, covers a large number of document shadow images.
CV
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】
lossy-vae
Authors' PyTorch implementation of a number of lossy image compression methods that are based on hierarchical VAEs
FPGA-MPEG2-encoder
FPGA-based high performance MPEG2 encoder for video compression. 基于 FPGA 的高性能 MPEG2 视频编码器，可实现视频压缩。
BSVD
[ACM MM 2022] Real-time Streaming Video Denoising with Bidirectional Buffers
paper-reading
深度学习经典、新论文逐段精读
edge-cloud-rac
Authors' PyTorch implementation of "Efficient Feature Compression for Edge-Cloud Systems"
MMNet
video denoising
openISP
Image Signal Processor
ffmpeg-build-script
The FFmpeg build script provides an easy way to build a static FFmpeg on OSX and Linux with non-free codecs included.
zynq_cam_isp_demo
基于verilog实现了ISP图像处理IP
video_codec_learn
关于视频编解码学习资料
CrowdFix
IEEE published Eye-tracking dataset of Human Eye Fixations over Crowd Videos. This dataset is part of the MIT/Tübingen Saliency Benchmark datasets.
PyTorchVideoCompression
PyTorch implementation and benchmark of Video Compression
FUIR
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. ⭐⭐⭐⭐⭐⭐
tempformer-xl
updating transformer-xl codebase
e200_opensource
Deprecated, please go to next generation Ultra-Low Power RISC-V Core https://github.com/riscv-mcu/e203_hbirdv2
ExtremeLowLight
Code&Dataset : Learning an Adaptive Model for Extreme Low-light Raw Image Processing
JM
h264 reference software from http://iphome.hhi.de/suehring/tml/download/