Pinned Repositories
AWNet-Attentive-Wavelet-Network-for-Image-ISP
Runner-Up solution in AIM 2020 Learned Image ISP challenge (ECCVW 2020)
CubePlusPlus
Cube++ is a novel dataset collected for illumination estimation problem. It has 4890 raw 18-megapixel images, each containing a SpyderCube color target in their scenes, manually labelled categories, and ground truth illumination chromaticities.
CycleISP
Official repository for "CycleISP: Real Image Restoration via Improved Data Synthesis" (CVPR 2020--Oral)
deep-learning
personal practice（个人练习，实现了深度学习中的一些算法，包括：四种初始化方法（zero initialize, random initialize, xavier initialize, he initialize），深度神经网络，正则化，dropout， 三种梯度下降方法(BGD, SGD, mini-batch)，六种优化算法(momentum、nesterov momentum、Adagrad、Adadelta、RMSprop、Adam)，梯度检验、batch normalization）、RNN
DeepISP
Deep learning does image processing
DeepLearning-500-questions
深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为15个章节，近20万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06
free-books
互联网上的免费书籍
ImageTools
这是一款图像相关的工具软件，扩展性好。目前集成有镜头计算器、抖动测试工具、看图工具、RAW图编辑（ISP算法的实现）等功能。可以方便的进行后期算法的验证
ISP
image signal process
reproducible-image-denoising-state-of-the-art
Collection of popular and reproducible image denoising works.
Bright-Shawn's Repositories
Bright-Shawn/reproducible-image-denoising-state-of-the-art
Collection of popular and reproducible image denoising works.
Bright-Shawn/AWNet-Attentive-Wavelet-Network-for-Image-ISP
Runner-Up solution in AIM 2020 Learned Image ISP challenge (ECCVW 2020)
Bright-Shawn/CubePlusPlus
Cube++ is a novel dataset collected for illumination estimation problem. It has 4890 raw 18-megapixel images, each containing a SpyderCube color target in their scenes, manually labelled categories, and ground truth illumination chromaticities.
Bright-Shawn/CycleISP
Official repository for "CycleISP: Real Image Restoration via Improved Data Synthesis" (CVPR 2020--Oral)
Bright-Shawn/deep-learning
personal practice（个人练习，实现了深度学习中的一些算法，包括：四种初始化方法（zero initialize, random initialize, xavier initialize, he initialize），深度神经网络，正则化，dropout， 三种梯度下降方法(BGD, SGD, mini-batch)，六种优化算法(momentum、nesterov momentum、Adagrad、Adadelta、RMSprop、Adam)，梯度检验、batch normalization）、RNN
Bright-Shawn/DeepISP
Deep learning does image processing
Bright-Shawn/DeepLearning-500-questions
深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为15个章节，近20万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06
Bright-Shawn/free-books
互联网上的免费书籍
Bright-Shawn/ImageTools
这是一款图像相关的工具软件，扩展性好。目前集成有镜头计算器、抖动测试工具、看图工具、RAW图编辑（ISP算法的实现）等功能。可以方便的进行后期算法的验证
Bright-Shawn/ISP
image signal process
Bright-Shawn/ISP-based-on-responses-prediction-model
Study on Methodology and Technology of Digital Camera Image signal Processing Based on Raw Responses Prediction Model
Bright-Shawn/mit-ml
斯坦福机器学习完整 python 实现
Bright-Shawn/pyOpenBCI
Provide a stable Python driver for all OpenBCI Biosensors.
Bright-Shawn/utils
供CDN方式调用的工具代码(自己写着用的)