Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ARtVista: Gateway To Empower Anyone Into Artist

Trong-Vu Hoang, Quang-Binh Nguyen, Duy-Nam Ly, Khanh-Duy Le, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le

TL;DR

The proposed ARtVista - a novel system integrating AR and generative AI technologies, empowering users to create visually stunning artwork devoid of the necessity for advanced drawing skills.

Abstract

Drawing is an art that enables people to express their imagination and emotions. However, individuals usually face challenges in drawing, especially when translating conceptual ideas into visually coherent representations and bridging the gap between mental visualization and practical execution. In response, we propose ARtVista - a novel system integrating AR and generative AI technologies. ARtVista not only recommends reference images aligned with users' abstract ideas and generates sketches for users to draw but also goes beyond, crafting vibrant paintings in various painting styles. ARtVista also offers users an alternative approach to create striking paintings by simulating the paint-by-number concept on reference images, empowering users to create visually stunning artwork devoid of the necessity for advanced drawing skills. We perform a pilot study and reveal positive feedback on its usability, emphasizing its effectiveness in visualizing user ideas and aiding the painting process to achieve stunning pictures without requiring advanced drawing skills. The source code will be available at https://github.com/htrvu/ARtVista.

ARtVista: Gateway To Empower Anyone Into Artist

TL;DR

The proposed ARtVista - a novel system integrating AR and generative AI technologies, empowering users to create visually stunning artwork devoid of the necessity for advanced drawing skills.

Abstract

Drawing is an art that enables people to express their imagination and emotions. However, individuals usually face challenges in drawing, especially when translating conceptual ideas into visually coherent representations and bridging the gap between mental visualization and practical execution. In response, we propose ARtVista - a novel system integrating AR and generative AI technologies. ARtVista not only recommends reference images aligned with users' abstract ideas and generates sketches for users to draw but also goes beyond, crafting vibrant paintings in various painting styles. ARtVista also offers users an alternative approach to create striking paintings by simulating the paint-by-number concept on reference images, empowering users to create visually stunning artwork devoid of the necessity for advanced drawing skills. We perform a pilot study and reveal positive feedback on its usability, emphasizing its effectiveness in visualizing user ideas and aiding the painting process to achieve stunning pictures without requiring advanced drawing skills. The source code will be available at https://github.com/htrvu/ARtVista.
Paper Structure (14 sections, 5 figures)

This paper contains 14 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. AR Drawing Tool
  4. Image Generation
  5. Image to Sketch
  6. ARtVista - Multimodal AR Generative Drawing System
  7. Conceptualization
  8. Prototype Implementation
  9. AR Interface:
  10. Image Generation Framework:
  11. Pilot study
  12. Study Setup
  13. Initial Insights
  14. Conclusion and Future Work

Figures (5)

  • Figure 1: ARtVista interface. a) Realistic reference image suggestion. b) Painting-style picture generating. c)-d) Composition of painting and sketch. e) AR view. f) Physical setup for ARtVista. g) Designed drawing paper.
  • Figure 2: Overview of image generation workflow with three main capabilities: reference image generation, sketch and painting generation, and paint-by-number game simulating.
  • Figure 3: The illustration for the output of some painting styles of our framework: Colorful painting, watercolor, and oil painting.
  • Figure 4: The workflow of automatic number painting regions process.
  • Figure 5: Paintings created by participants using ARtVista.