Image Generation On Imagenet 32X32

Metrics

bpd

Results

Performance results of various models on this benchmark

		Paper Title
Real NVP (Dinh et al., 2017)	4.28	Density estimation using Real NVP
Glow (Kingma and Dhariwal, 2018)	4.09	Glow: Generative Flow with Invertible 1x1 Convolutions
MintNet	4.06	MintNet: Building Invertible Neural Networks with Masked Convolutions
Residual Flow	4.01	Residual Flows for Invertible Generative Modeling
BIVA Maaloe et al. (2019)	3.96	BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
NVAE w/ flow	3.92	NVAE: A Deep Hierarchical Variational Autoencoder
ANF Huang et al. (2020)	3.92	Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
DDPM	3.89	Denoising Diffusion Probabilistic Models
PixelRNN	3.86	Pixel Recurrent Neural Networks
Flow++	3.86	Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
SPN Menick and Kalchbrenner (2019)	3.85	Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
DDPM++ (VP, NLL) + ST	3.85	Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
Gated PixelCNN	3.83	Conditional Image Generation with PixelCNN Decoders
Very Deep VAE	3.8	Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
δ-VAE	3.77	Preventing Posterior Collapse with delta-VAEs
MRCNF	3.77	Multi-Resolution Continuous Normalizing Flows
Image Transformer	3.77	Image Transformer
ScoreFlow	3.76	Maximum Likelihood Training of Score-Based Diffusion Models
Hourglass	3.74	Hierarchical Transformers Are More Efficient Language Models
Reflected Diffusion	3.74	Reflected Diffusion Models

0 of 33 row(s) selected.

Command Palette

Image Generation On Imagenet 32X32

Metrics

Results

Command Palette

Image Generation On Imagenet 32X32

Metrics

Results