cain4318 Goto Github PK

adversarialnetspapers

The classical papers and codes about generative adversarial nets

cnn-models

ImageNet pre-trained models with batch normalization for the Caffe framework

crl

Implementation of the paper "Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching"

deep-learning

Some practices about deep learning

deep-stereo

Use deep learning to estimate virtual views

deeplearning

Resource about deeplearning

emd

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

high-res-neural-inpainting

High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis

itorch

IPython kernel for Torch with visualization and plotting

lecp

Largest Empty Convex Polygon

lift

Code release for the ECCV 2016 paper

mc-cnn

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

mobilenet

MobileNet build with Tensorflow

monodepth

Unsupervised single image depth prediction with CNNs

nn

pix2pix

Image-to-image translation using conditional adversarial nets

places365

The Places365-CNNs for Scene Classification

rendering

resmatch

Implementation of "Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning"

stnbhwd

Modules for spatial transformer networks (BHWD layout)

tensorflow-deeplab-v3-plus

DeepLabv3+ built in TensorFlow

torch7

http://torch.ch

unsupervised_depth_estimation

Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue

view-synthesis-for-lfc

implementation based on Learning-Based View Synthesis for Light Field Cameras (Siggraph Asia 2016)

w-net

w-net: a convolutional neural network architecture for the self-supervised learning of depthmap from pairs of stereo images.