2021
DOI: 10.1007/s41095-021-0227-7
|View full text |Cite
|
Sign up to set email alerts
|

DualFace: Two-stage drawing guidance for freehand portrait sketching

Abstract: Special skills are required in portrait painting, such as imagining geometric structures and facial detail for final portrait designs. This makes it a difficult task for users, especially novices without prior artistic training, to draw freehand portraits with high-quality details. In this paper, we propose dualFace, a portrait drawing interface to assist users with different levels of drawing skills to complete recognizable and authentic face sketches. Inspired by traditional artist workflows for portrait dra… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
3
3

Relationship

2
7

Authors

Journals

citations
Cited by 27 publications
(5 citation statements)
references
References 38 publications
0
5
0
Order By: Relevance
“…MichiGAN [32] explicitly disentangles hair into four orthogonal attributes and designs a corresponding condition module to process user inputs for each attribute. DualFace [33] proposes a two-stage guidance system to help users produce detailed portrait sketches with data-driven global guidance and GAN-based local guidance. InterFaceGAN [34] explores disentanglement of various semantic attributes and edits several attributes using linear editing paths.…”
Section: Facial Image Manipulation With Gansmentioning
confidence: 99%
“…MichiGAN [32] explicitly disentangles hair into four orthogonal attributes and designs a corresponding condition module to process user inputs for each attribute. DualFace [33] proposes a two-stage guidance system to help users produce detailed portrait sketches with data-driven global guidance and GAN-based local guidance. InterFaceGAN [34] explores disentanglement of various semantic attributes and edits several attributes using linear editing paths.…”
Section: Facial Image Manipulation With Gansmentioning
confidence: 99%
“…DualMotion adopted a two-stage scheme with both global and local stages [26], [27]. Along with the perception capabilities of human, designing the target with a bottom-up scheme is difficult.…”
Section: Creativity Support With Two-stage Schemementioning
confidence: 99%
“…In such cases, some researches 2 analyze layout sketches to retrieve the web page to give user references when designing, and other researches 3,4 analyze the sketch stroke to edit the image. Previous studies 5,6 have also used user sketches to provide shadow guidance to enhance user design abilities, which can be used in motion retrieval 7 and calligraphy. 8 The design interfaces have been proposed for cartoon image generation 9 and facial images.…”
Section: Related Workmentioning
confidence: 99%