Randomized Gaussian-guided quantization of thermal images reduces overfitting for few-shot diffusion super-resolution on a new drone infrared benchmark, but baseline comparisons are not training-matched and the diffusion conditioning is unspecified.
Exploiting diffusion prior for real-world image super-resolution,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DroneSR: Rethinking Few-shot Thermal Image Super-Resolution from Drone-based Perspective
Randomized Gaussian-guided quantization of thermal images reduces overfitting for few-shot diffusion super-resolution on a new drone infrared benchmark, but baseline comparisons are not training-matched and the diffusion conditioning is unspecified.