Image Completion on CIFAR-10
This is an incremental improvement for image in-painting tasks in computer vision.
The project tackled image completion on the CIFAR-10 dataset, achieving a mean squared error of 0.015 with a deep fully convolutional network that produced realistic in-painted images.
This project performed image completion on CIFAR-10, a dataset of 60,000 32x32 RGB images, using three different neural network architectures: fully convolutional networks, convolutional networks with fully connected layers, and encoder-decoder convolutional networks. The highest performing model was a deep fully convolutional network, which was able to achieve a mean squared error of .015 when comparing the original image pixel values with the predicted pixel values. As well, this network was able to output in-painted images which appeared real to the human eye.