Intelligent Painter: New Masking Strategy and Self- Referencing with Resampling

Chun Chuen Hui, Wan Chi Siu, Ngai Fong Law, H. Anthony Chan

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Painting with our own hands is not everyone's talent. Some of us may dream big to create our own artwork but do not have the ability to do so. With the help of deep learning techniques, we nowadays can generate text-based painting. However, just typing text to create our own artwork is still different from doing it yourself (DIY). We proposed an application called intelligent painter, which can let users decide the placement of the objects and use the diffusion models to fill all the gaps after the users finish their placement. In this paper, we propose two major contributions to make better generation of images by (i) a new masking strategy and (ii) speeding up the process by 50% compared with resampling Denoising Diffusion Probabilistic Models (DDPM), with a self-pre-processing input step.

Original languageEnglish
Title of host publication2023 24th International Conference on Digital Signal Processing, DSP 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350339598
DOIs
Publication statusPublished - Jun 2023
Event24th International Conference on Digital Signal Processing, DSP 2023 - Rhodes, Greece
Duration: 11 Jun 202313 Jun 2023

Publication series

NameInternational Conference on Digital Signal Processing, DSP
Volume2023-June

Conference

Conference24th International Conference on Digital Signal Processing, DSP 2023
Country/TerritoryGreece
CityRhodes
Period11/06/2313/06/23

Keywords

  • Deep learning
  • Diffusion model
  • Image processing
  • Image synthesis Introduction
  • intelligent painter

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'Intelligent Painter: New Masking Strategy and Self- Referencing with Resampling'. Together they form a unique fingerprint.

Cite this