Generating Diverse High-Resolution Images With VQ-VAE

Toggle navigationOpenReview.net
  • Login
Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Recommendations. Open Directory. Open API. Open Source.

Generating Diverse High-Resolution Images with VQ-VAEDownload PDF

Ali Razavi, Aaron van den Oord, Oriol Vinyals

Published: 03 May 2019, Last Modified: 05 May 2023DeepGenStruct 2019Readers: EveryoneKeywords: Vector Quantization, Autoregressive models, Generative ModelsTL;DR: scale and enhance VQ-VAE with powerful priors to generate near realistic images.Abstract: We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation. To this end, we scale and enhance the autoregressive priors used in VQ-VAE to generate synthetic samples of much higher coherence and fidelity than possible before. We use simple feed-forward encoder and decoder networks, thus our model is an attractive candidate for applications where the encoding and decoding speed is critical. Additionally, this allows us to only sample autoregressively in the compressed latent space, which is an order of magnitude faster than sampling in the pixel space, especially for large images. We demonstrate that a multi-scale hierarchical organization of VQ-VAE, augmented with powerful priors over the latent codes, is able to generate samples with quality that rivals that of state of the art Generative Adversarial Networks on multifaceted datasets such as ImageNet, while not suffering from GAN's known shortcomings such as mode collapse and lack of diversity.3 RepliesLoading

Send Feedback

Enter your feedback below and we'll get back to you as soon as possible. To submit a bug report or feature request, you can use the official OpenReview GitHub repository:Report an issue

Select a topic or type what you need help withCancelSend

BibTeX Record

Click anywhere on the box above to highlight complete recordDone

Từ khóa » Vq Vae Image Compression