Applying multiple guidance gradient updates per denoising step improves LPIPS and PSNR for super-resolution and deblurring on natural and aerial images, and runs in real time on a Jetson Orin Nano, though the per-step sweep is not reported.
McCann, Marc L.Klasky, and JongChul Ye
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
-
Multi-Step Guided Diffusion for Image Restoration on Edge Devices: Toward Lightweight Perception in Embodied AI
Applying multiple guidance gradient updates per denoising step improves LPIPS and PSNR for super-resolution and deblurring on natural and aerial images, and runs in real time on a Jetson Orin Nano, though the per-step sweep is not reported.