Regularized vector quantization for tokenized image synthesis

J Zhang, F Zhan, C Theobalt… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Quantizing images into discrete representations has been a fundamental problem in unified
generative modeling. Predominant approaches learn the discrete representation either in a …

Regularized Vector Quantization for Tokenized Image Synthesis

J Zhang, F Zhan, C Theobalt, S Lu - 2023 IEEE/CVF Conference on …, 2023 - computer.org
Quantizing images into discrete representations has been a fundamental problem in unified
generative modeling. Predominant approaches learn the discrete representation either in a …

[PDF][PDF] Regularized Vector Quantization for Tokenized Image Synthesis

J Zhang, F Zhan, C Theobalt, S Lu - 36th IEEE/CVF Conference on …, 2023 - pure.mpg.de
Quantizing images into discrete representations has been a fundamental problem in unified
generative modeling. Predominant approaches learn the discrete representation either in a …

Regularized Vector Quantization for Tokenized Image Synthesis

J Zhang, F Zhan, C Theobalt, S Lu - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
Quantizing images into discrete representations has been a fundamental problem in unified
generative modeling. Predominant approaches learn the discrete representation either in a …

Regularized Vector Quantization for Tokenized Image Synthesis

J Zhang, F Zhan, C Theobalt… - 2023 IEEE/CVF …, 2023 - ieeexplore.ieee.org
Quantizing images into discrete representations has been a fundamental problem in unified
generative modeling. Predominant approaches learn the discrete representation either in a …

[PDF][PDF] Regularized Vector Quantization for Tokenized Image Synthesis

J Zhang, F Zhan, C Theobalt, S Lu - researchgate.net
Quantizing images into discrete representations has been a fundamental problem in unified
generative modeling. Predominant approaches learn the discrete representation either in a …

Regularized Vector Quantization for Tokenized Image Synthesis

J Zhang, F Zhan, C Theobalt, S Lu - arXiv preprint arXiv:2303.06424, 2023 - arxiv.org
Quantizing images into discrete representations has been a fundamental problem in unified
generative modeling. Predominant approaches learn the discrete representation either in a …