Bilkent University
Department of Computer Engineering

---

CS 590/690 SEMINAR

 

Harmonizing Focused Embeddings for Object Removal on Images Using Denoising Diffusion Models

 

Yiğit Ekin
Master Student
(Supervisor: Asst. Prof.Ayşegül Dündar Boral)

Computer Engineering Department
Bilkent University

Abstract: Advanced image editing techniques, particularly inpainting, are essential for seamlessly removing unwanted elements while preserving visual integrity. Traditional GAN-based methods have achieved notable success, but recent advancements in diffusion models have produced superior results due to their training on large-scale datasets, enabling the generation of remarkably realistic inpainted images. Despite their strengths, diffusion models often struggle with object removal tasks without explicit guidance, leading to unintended hallucinations of the removed object. To address this issue, we introduce a novel approach leveraging CLIP embeddings to focus on background regions while excluding foreground elements. Our method enhances inpainting accuracy and quality by identifying embeddings that prioritize the background, thus achieving seamless object removal. Unlike other methods that rely on specialized training datasets or costly manual annotations, our method provides a flexible, plug-and-play solution compatible with various diffusion-based inpainting techniques

 

DATE: March 24, Monday @ 13:20 Place: EA 502