Luo Ziwei

cs. PhD

[Luo Ziwei @ZiweiRo]

Excited to announce that our work "Image Restoration with Mean-Reverting Stochastic Differential Equations" has been accepted at #ICML2023🎉. Congrats to our amazing team and coauthors for this great work.

Paper: https://t.co/lvwWPInxmX
Project: https://t.co/mdpHIfS8fq

[Luo Ziwei @ZiweiRo]

Global confidence is a key to diffusion sampling: a general training-free and reward-free approach for masked diffusion language models.

[Fredrik K. Gustafsson @fregu856]

Our paper "Controlling Vision-Language Models for Multi-Task Image Restoration" will be presented at #ICLR2024 next week.

Paper: https://t.co/0HMsmRKEF4
Code: https://t.co/40ugzMWbPU
Project page: https://t.co/nni7nu4Vrx

Work lead by @ZiweiRo, with collaborators in Uppsala.

[Luo Ziwei @ZiweiRo]

@du_yilun Very interesting workshop!! Can we directly submit a paper that is under review in ICML 2024?

[Luo Ziwei @ZiweiRo]

@6___0 @camenduru @fregu856 @dreamingtulpa Please also see the notice document: https://t.co/JocrO0ZCX1

And this discussion:
https://t.co/aShw38kK7b

[Sylvain Filoni @fffiloni]

Just released on @huggingface a quick @gradio demo for DA-CLIP presented below by @dreamingtulpa

Works like a charm, just drop your damaged image and hit submit !

Try it ! DA-CLIP demo link: https://t.co/MJyfbypBbx

[camenduru @camenduru]

Universal Image Restoration Colab 🥳 Thanks to Ziwei Luo ❤ @fregu856 ❤ Zheng Zhao ❤ Jens Sjölund ❤ Thomas B. Schön ❤

🌐page: https://t.co/kWhY90rkjq
📄paper: https://t.co/EM5dXRtkgM
🧬code: https://t.co/NdNroFVPiz
🦒colab: please try it 🐣 https://t.co/50jfYTmOK8

[Luo Ziwei @ZiweiRo]

@fffiloni @huggingface @Gradio @dreamingtulpa Hi, I provide more example LQ images in the Google Drive from our test dataset and welcome to test them: https://t.co/EOxF23fW3k

[Dreaming Tulpa 🥓👑 @dreamingtulpa]

There is a new image restoration method in town called DA-CLIP.

The method is able to restore images by dehazing, deblurring, denoising, derainining, desnowing, removing unwanted shadows, raindrops, or improving lighting. So, basically from everything 😅

https://t.co/tJtaSKjC2b

[Luo Ziwei @ZiweiRo]

@fffiloni @huggingface @Gradio @dreamingtulpa Great work, thanks!!!

[AK @_akhaliq]

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

abs: https://t.co/2jL4j6yEj6
github: https://t.co/ObEWum1BEy