78%Highly rated
?Highly ratedVote to see the score
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
DC-SAE combines semantic and pixel-level encoders to achieve 32x compression with high fidelity and faster diffusion convergence. It achieves 29.79 PSNR and 3.37 gFID on ImageNet 512x512, outperforming prior high-compression tokenizers by large margins.
Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 42 on Hugging Face · Code ★ 18
– ReadersNo votes yet
11/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 11 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 1/5