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.
Improved denoising diffusion probabilis- tic models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
baseline 1polarities
baseline 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.