Chain-of-Zoom factorizes extreme super-resolution into an autoregressive sequence of intermediate scales using a reused backbone model plus GRPO-tuned multi-scale VLM prompts.
Scaling up to excellence: Practicing model scaling for photo-realistic image restoration in the wild
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
SANA-SR uses 32x deep compression autoencoding and linear-attention DiT to deliver competitive real-world image super-resolution at 0.019s inference after pruning.
citing papers explorer
-
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
Chain-of-Zoom factorizes extreme super-resolution into an autoregressive sequence of intermediate scales using a reused backbone model plus GRPO-tuned multi-scale VLM prompts.
-
Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
SANA-SR uses 32x deep compression autoencoding and linear-attention DiT to deliver competitive real-world image super-resolution at 0.019s inference after pruning.