Corpus ID: 237532266

SketchHairSalon: Deep Sketch-based Hair Image Synthesis

@article{Xiao2021SketchHairSalonDS,
  title={SketchHairSalon: Deep Sketch-based Hair Image Synthesis},
  author={Chufeng Xiao and Deng Yu and Xiaoguang Han and Youyi Zheng and Hongbo Fu},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.07874}
}
  • Chufeng Xiao, Deng Yu, +2 authors Hongbo Fu
  • Published 16 September 2021
  • Computer Science
  • ArXiv
Fig. 1. Our SketchHairSalon system allows users to easily create photo-realistic hair images with various hairstyles (e.g., straight, wavy, braided) from freehand sketches (Left-Top in each example), containing colored hair strokes and non-hair strokes (in black). Our two-stage framework automatically generates both hair mattes (Left-Bottom in each example) and hair images (Right in each example) directly from such sketches. Original images courtesy of Jacob Rabin, Peteselfchoose, Apostolos… Expand

References

SHOWING 1-10 OF 42 REFERENCES
DeepSketchHair: Deep Sketch-Based 3D Hair Modeling
TLDR
DeepSketchHair, a deep learning based tool for modeling of 3D hair from 2D sketches, takes as input a user-drawn sketch, and automatically generates a3D hair model, matching the input sketch. Expand
Sketching hairstyles
TLDR
An intuitive sketching interface for interactive hairstyle design, made possible by an efficient numerical updating scheme based on a vector field representation obtained by solving a sparse linear system with the style curves acting as boundary constraints. Expand
Intuitive, Interactive Beard and Hair Synthesis With Generative Models
TLDR
A neural network pipeline is employed that synthesizes realistic and detailed images of facial hair directly in the target image in under one second, controlled by simple and sparse guide strokes from the user defining the general structural and color properties of the target hairstyle. Expand
Dynamic hair manipulation in images and videos
TLDR
This paper solves an unambiguous 3D vector field explicitly from the image and adopts an iterative hair generation algorithm to create hair models that not only visually match the original input very well but also possess physical plausibility. Expand
A generative sketch model for human hair analysis and synthesis
  • Hong Chen, Song-Chun Zhu
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2006
TLDR
The generative model provides a straightforward way for synthesizing realistic hair images and stylistic drawings (rendering) from a sketch graph and a few Gaussian bases. Expand
MichiGAN: multi-input-conditioned hair image generation for portrait editing
TLDR
MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation that allows fully-conditioned hair generation from multiple user inputs, is presented. Expand
Modeling hair from an RGB-D camera
TLDR
This paper introduces a fully automatic, data-driven approach to model the hair geometry and compute a complete strand-level 3D hair model that closely resembles the input from a single RGB-D camera. Expand
Single-view hair modeling using a hairstyle database
TLDR
A novel data-driven framework that can digitize complete and highly complex 3D hairstyles from a single-view photograph and is compared with state-of-the-art hair modeling algorithms is introduced. Expand
Sketch interface based expressive hairstyle modelling and rendering
We present a new system for interactively modeling and rendering nonphotorealistic hairstyles. The system is featured with a user-friendly sketch interface allowing a user generate his/her desiredExpand
Real-Time Hair Rendering Using Sequential Adversarial Networks
TLDR
This work presents an adversarial network for rendering photorealistic hair as an alternative to conventional computer graphics pipelines and introduces an intermediate edge activation map to orientation field conversion step to ensure a successful CG-to-photoreal transition, while preserving the hair structures of the original input data. Expand
...
1
2
3
4
5
...