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.
Note that this step requires multiple passes of the VLM, a computational bottleneck to be solved by future work
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
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.