扩散
计算机科学
图像质量
图像(数学)
算法
人工智能
各项异性扩散
自回归模型
模式识别(心理学)
编码(内存)
图像分辨率
自编码
计算机视觉
数学
深度学习
物理
统计
热力学
作者
Shuyang Gu,Dong Chen,Jianmin Bao,Fang Wen,Bo Zhang,Dongdong Chen,Yuan Liu,Baining Guo
标识
DOI:10.1109/cvpr52688.2022.01043
摘要
We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent space is modeled by a conditional variant of the recently developed Denoising Diffusion Probabilistic Model (DDPM). We find that this latent-space method is well-suited for text-to-image generation tasks because it not only eliminates the unidirectional bias with existing methods but also allows us to incorporate a mask-and-replace diffusion strategy to avoid the accumulation of errors, which is a serious problem with existing methods. Our experiments show that the VQ-Diffusion produces significantly better text-to-image generation results when compared with conventional autoregressive (AR) models with similar numbers of parameters. Compared with previous GAN-based text-to-image methods, our VQ-Diffusion can handle more complex scenes and improve the synthesized image quality by a large margin. Finally, we show that the image generation computation in our method can be made highly efficient by reparameterization. With traditional AR methods, the text-to-image generation time increases linearly with the output image resolution and hence is quite time consuming even for normal size images. The VQ-Diffusion allows us to achieve a better trade-off between quality and speed. Our experiments indicate that the VQ-Diffusion model with the reparameterization is fifteen times faster than traditional AR methods while achieving a better image quality. The code and models are available at https://github.com/cientgu/VQ-Diffusion.
科研通智能强力驱动
Strongly Powered by AbleSci AI