Proceedings of the 28th ACM International Conference on Multimedia 2020
DOI: 10.1145/3394171.3413873
|View full text |Cite
|
Sign up to set email alerts
|

Deep Shapely Portraits

Abstract: Figure 1: Given input portrait images with varying poses and expressions (bottom), our approach can automatically generate shapely portraits (top) that are better proportioned, by estimating the best reshaping parameter setting (called shapely degree) using deep learning.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
15
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
3

Relationship

3
4

Authors

Journals

citations
Cited by 10 publications
(15 citation statements)
references
References 38 publications
0
15
0
Order By: Relevance
“…For reducing image distortion after face editing, content-aware image warping becomes a powerful tool in a wide range of editing applications [11] [19] [27]. However, it is challenging to generate continuous and stable deformations across all video frames because the mappings from source to target of consecutive frames are usually inconsistent.…”
Section: Portrait Video Deformationmentioning
confidence: 99%
See 3 more Smart Citations
“…For reducing image distortion after face editing, content-aware image warping becomes a powerful tool in a wide range of editing applications [11] [19] [27]. However, it is challenging to generate continuous and stable deformations across all video frames because the mappings from source to target of consecutive frames are usually inconsistent.…”
Section: Portrait Video Deformationmentioning
confidence: 99%
“…Xiao et al [27] proposed a reshaping model to generate reshaped portrait images based on an estimated adjusting parameter. We extend this method from reshaping one monocular image to reshaping the whole image sequence.…”
Section: D Face Reshapingmentioning
confidence: 99%
See 2 more Smart Citations
“…Portrait photography retouching is widely used in various fields, such as social media, weddings, and advertisements. While automatic face reshaping is well researched [18,24,28,33] and employed in many applications (e.g., Instagram, Tictok), automatic body reshaping, which generally aims to make figure looks more shapely and attractive, is still far from being settled due to the complicated structure and appearance of human bodies. In fact, body reshaping is a troublesome task even for professional artists.…”
Section: Introductionmentioning
confidence: 99%