HyperAIHyperAI超神经
首页算力平台文档资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Image Generation On Celeba 256X256

评估指标

bpd

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
Glow (Kingma and Dhariwal, 2018)1.03Glow: Generative Flow with Invertible 1x1 Convolutions
Residual Flow0.992Residual Flows for Invertible Generative Modeling
MaCow (Unf)0.95MaCow: Masked Convolutional Generative Flow
Locally Masked PixelCNN0.74Locally Masked Convolution for Autoregressive Models
ANF Huang et al. (2020)0.72Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
LSGM0.70Score-based Generative Modeling in Latent Space
NVAE w/ flow0.70NVAE: A Deep Hierarchical Variational Autoencoder
MaCow (Var)0.67MaCow: Masked Convolutional Generative Flow
SPN Menick and Kalchbrenner (2019)0.61Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling-
Efficient-VDVAE0.51Efficient-VDVAE: Less is more
StyleSwin-StyleSwin: Transformer-based GAN for High-resolution Image Generation
NCP-VAE-A Contrastive Learning Approach for Training Variational Autoencoder Priors-
HiT-B-Improved Transformer for High-Resolution GANs
StyleALAE-Adversarial Latent Autoencoders
GLF+perceptual loss (ours)-Generative Latent Flow
MSP-Latent Space Factorisation and Manipulation via Matrix Subspace Projection
VQGAN-Taming Transformers for High-Resolution Image Synthesis
0 of 17 row(s) selected.
Image Generation On Celeba 256X256 | SOTA | HyperAI超神经