Neural Knitworks: Patched Neural Implicit Representation Networks

arXiv:2109.14406v2 Announce Type: replace
Abstract: Coordinate-based Multilayer Perceptron (MLP) networks, despite being capable of learning neural implicit representations, are not performant for internal image synthesis applications. Convolutional Neural Networks (CNNs) are typically used instead for a variety of internal generative tasks, at the cost of a larger model. We propose Neural Knitwork, an architecture for neural implicit representation learning of natural images that achieves image synthesis by optimizing the distribution of image patches in an adversarial manner and by enforcing …

abstract applications arxiv cnns convolutional neural networks cost cs.ai cs.cv cs.gr generative image mlp networks neural networks perceptron representation synthesis tasks type