A single diffusion L2 loss can train scalable image tokenizers that match or outperform GAN-LPIPS tokenizers for reconstruction and downstream generation.
BEiT : B ert pre-training of image transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Diffusion Autoencoders are Scalable Image Tokenizers
A single diffusion L2 loss can train scalable image tokenizers that match or outperform GAN-LPIPS tokenizers for reconstruction and downstream generation.