Daclip-Uir

Visit Tool

daclip-uir is an open-source PyTorch implementation for universal image restoration, controlling vision-language models to enhance image quality. It was recognized in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is daclip-uir?

daclip-uir provides an official PyTorch implementation for controlling vision-language models, specifically designed for universal image restoration tasks. This tool can address various image degradations such as motion blur, haze, JPEG compression, low-light conditions, noise, raindrops, rain, shadows, snow, and uncompleted images (inpainting). It offers pretrained models for degradation-aware CLIP and universal image restoration, along with a Gradio app for easy testing of custom images. The project also includes a follow-up work focusing on photo-realistic image restoration and handling real-world mixed-degradation images, demonstrating its continuous development and robust capabilities in the field.

Best used for

Ideal for researchers and developers who need to implement and experiment with advanced image restoration techniques using vision-language models. Especially valuable for addressing diverse image degradations like blur, haze, noise, and low-light, and for contributing to or building upon open-source AI models.

Common actions

restore images

enhance image quality

remove image degradation

research vision-language models

github copilotface swapping"AI Agents"workflowscollaborationautomated workflowopen-sourcelow-code/no-codedeepfake

Capabilities

Key features

Universal image restoration
Degradation-aware CLIP models
Multiple degradation types
Pretrained weights available
Gradio app for testing
PyTorch implementation

Target Audience

professor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What types of image degradations can daclip-uir restore?

daclip-uir is designed for universal image restoration, capable of handling various degradations including motion blur, haze, JPEG compression, low-light, noise, raindrops, rain, shadows, snow, and uncompleted images (inpainting). It aims to provide a comprehensive solution for diverse image quality issues.

Is daclip-uir suitable for real-world images?

While daclip-uir performs well on its training dataset, the developers note that processing some real-world images with distribution shifts (e.g., different devices, resolutions) can still be challenging. They are actively working on making the model more practical for such scenarios.

How can I test daclip-uir with my own images?

You can test daclip-uir using the provided Gradio app. After downloading the pretrained weights and modifying the model path in the options file, simply run `python app.py` to open a local web interface where you can upload and process your images.

Trending

Subcategories trending in Content & Design

Image Generation AI Writing Assistants Audio & Music Video Generation Graphic Design Video Editing

Trending

Also listed in

This tool also appears in

Research & Education › Academic Research Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce