Refusion: Enabling Large-Size Realistic Image Restoration With Latent-Space Diffusion Models

Refusion : Enabling Large-Size Realistic Image Restoration With Latent-Space Diffusion Models

Luo, Ziwei (författare): Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens

Gustafsson, Fredrik K. (författare): Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens

Zhao, Zheng (författare): Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens

Sjölund, Jens, Biträdande lektor, 1987- (författare): Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens

Schön, Thomas B., Professor, 1977- (författare): Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens

(creator_code:org_t)

Institute of Electrical and Electronics Engineers (IEEE), 2023
2023
Engelska.
Ingår i: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1680-1691

Relaterad länk:: https://urn.kb.se/re...; visa fler...; https://doi.org/10.1...; visa färre...

Abstract Ämnesord

Stäng

This work aims to improve the applicability of diffusion models in realistic image restoration. Specifically, we enhance the diffusion model in several aspects such as network architecture, noise level, denoising steps, training image size, and optimizer/scheduler. We show that tuning these hyperparameters allows us to achieve better performance on both distortion and perceptual scores. We also propose a U-Net based latent diffusion model which performs diffusion in a low-resolution latent space while preserving high-resolution information from the original input for the decoding process. Compared to the previous latent-diffusion model which trains a VAE-GAN to compress the image, our proposed U-Net compression strategy is significantly more stable and can recover highly accurate images without relying on adversarial optimization. Importantly, these modifications allow us to apply diffusion models to various image restoration tasks, including real-world shadow removal, HR non-homogeneous dehazing, stereo super-resolution, and bokeh effect transformation. By simply replacing the datasets and slightly changing the noise network, our model, named Refusion, is able to deal with large-size images (e.g., 6000 x 4000 x 3 in HR dehazing) and produces good results on all the above restoration problems. Our Refusion achieves the best perceptual performance in the NTIRE 2023 Image Shadow Removal Challenge and wins 2nd place overall.

Av författaren/redakt...: Luo, Ziwei; Gustafsson, Fred ...; Zhao, Zheng; Sjölund, Jens, B ...; Schön, Thomas B. ...

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Signalbehandling

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.