Global context with discrete diffusion in vector quantised modelling for image generation

• Main Authors: Hu, Minghui, Wang, Yujie, Cham, Tat-Jen, Yang, Jianfei, Suganthan, Ponnuthurai Nagaratnam
• 其他作者: School of Computer Science and Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2023
• 主題: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; Visualization; Image Resolution
• 在線閱讀: https://hdl.handle.net/10356/172658

The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) with autoregressive models as generation part has yielded high-quality results on image generation. However, the autoregressive models will strictly follow the progressive scanning order during the sampling phase. This leads the ex...