Generating Diverse High-Resolution Images With VQ-VAE
Có thể bạn quan tâm
Toggle navigationOpenReview.net
Generating Diverse High-Resolution Images with VQ-VAE
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 RepliesLoadingSend 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 withCancelSendBibTeX Record
Click anywhere on the box above to highlight complete recordDoneTừ khóa » Vq Vae Image Compression
-
Fred's PhD Thesis Project: VQ VAE 2 Image Compression - GitHub
-
[PDF] Hierarchical Quantized Autoencoders - ArXiv
-
[PDF] Generating Diverse High-Fidelity Images With VQ ... - NIPS Papers
-
Generating Diverse High-Fidelity Images With VQ ... - NIPS Papers
-
Understanding VQ-VAE (DALL-E Explained Pt. 1) - ML@B Blog
-
Hierarchical Quantized Autoencoders - Papers With Code
-
[PDF] Generating Diverse High-Fidelity Images With VQ-VAE-2
-
[PDF] Soft Then Hard: Rethinking The Quantization In Neural Image ...
-
Generating Diverse High-fidelity Images With VQ-VAE-2
-
Almost Any Image Is Only 8k Vectors | By Ajit Rajasekharan
-
[PDF] ONLINE LEARNED CONTINUAL COMPRESSION WITH STACKED ...
-
[PDF] PILC: Practical Image Lossless Compression With An End-to-End ...
-
Standard Compression VQ-VAE And Its Reconstruction. Radiologists...
-
[PDF] Vector Quantization-Based Regularization For Autoencoders