CLOVA-X Image Editing: The Pixel Magic Unveiled by AI
Date:
DAN 24 Technical Talk: AI Eraser - Detailed Development Process of an Image Editing Service
This session will cover the detailed development process of AI Eraser, an image editing service based on image generation models in HyperCLOVA X. We will share various challenges encountered during the development of this service model, along with their solutions, efforts to enhance performance, and other key insights.
Session Overview
This session will be divided into two parts:
Segmentation
- Sharing the Image Segmentation Model, the core technology behind AI Eraser.
- Experiences with NAVER Segmentation Foundation Model research.
- The process of constructing data.
- Know-how to improve the performance of the model.
Generation
- Sharing the Image Generation Model that erases object areas based on segmentation results.
- Limitations of public models and ways to overcome them.
- The process of selecting necessary data and obtaining annotations suitable for model learning.
- Various methods to achieve natural editing results.
Table of Contents
1. Introduction to Image Editing Services and Pipeline
2. Segmentation
- Introduction to the Segmentation Task and Model Overview
- Introduction to the NAVER Segmentation Foundation Model
3. Generation
- Introduction to Diffusion and Overview of Applicable Services
- Object Removal
- Object Insertion
- Background Replacement
