Global context with discrete diffusion in vector quantised modelling for image generation
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...
Saved in:
Main Authors: | Hu, Minghui, Wang, Yujie, Cham, Tat-Jen, Yang, Jianfei, Suganthan, Ponnuthurai Nagaratnam |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172658 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
UniD3: unified discrete diffusion for simultaneous vision-language generation
by: Hu, Minghui, et al.
Published: (2023) -
Pluralistic free-form image completion
by: Zheng, Chuanxia, et al.
Published: (2023) -
Bridging global context interactions for high-fidelity image completion
by: Zheng, Chuanxia, et al.
Published: (2023) -
Shading‐based surface recovery using subdivision‐based representation
by: Deng, Teng, et al.
Published: (2020) -
Pluralistic image completion
by: Zheng, Chuanxia, et al.
Published: (2020)