Two‐phase Hair Image Synthesis by Self‐Enhancing Generative Model

  title={Two‐phase Hair Image Synthesis by Self‐Enhancing Generative Model},
  author={Haonan Qiu and Chuan Wang and Hang Zhu and Xiangyu Zhu and Jinjin Gu and Xiaoguang Han},
  journal={Computer Graphics Forum},
Generating plausible hair image given limited guidance, such as sparse sketches or low-resolution image, has been made possible with the rise of Generative Adversarial Networks (GANs. [...] Key Method The two-phase pipeline first generates a coarse image by an existing image translation model, then applies a re-generating network with self-enhancing capability to the coarse image.Expand
MichiGAN: multi-input-conditioned hair image generation for portrait editing
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
Despite the recent success of face image generation with GANs, conditional hair editing remains challenging due to the under-explored complexity of its geometry and appearance. In this paper, weExpand
SketchHairSalon: Deep Sketch-based Hair Image Synthesis
The SketchHairSalon system allows users to easily create photo-realistic hair images with various hairstyles from freehand sketches, containing colored hair strokes and non-hair strokes (in black). Expand
Semi-Supervised Skin Detection by Network With Mutual Guidance
  • Yi He, Jiayuan Shi, +5 authors Jue Wang
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
Experimental results show the effectiveness of the proposed dual-task neural network for joint detection of skin and body via a semi-supervised learning strategy outperforms the state-of-the-art in skin detection. Expand
Content-Aware Unsupervised Deep Homography Estimation
This work proposes an unsupervised deep homography method with a new architecture design that outperforms the state-of-the-art including deep solutions and feature-based solutions. Expand
Neural Hair Rendering
A generic neural-based hair rendering pipeline that can synthesize photo-realistic images from virtual 3D hair models that adopts an unsupervised solution to work on arbitrary hair models, which generates realistic renderings conditioned by extra appearance inputs. Expand


Real-Time Hair Rendering Using Sequential Adversarial Networks
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
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
A new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) is presented, which significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing. Expand
Scribbler: Controlling Deep Image Synthesis with Sketch and Color
A deep adversarial image synthesis architecture that is conditioned on sketched boundaries and sparse color strokes to generate realistic cars, bedrooms, or faces is proposed and demonstrates a sketch based image synthesis system which allows users to scribble over the sketch to indicate preferred color for objects. Expand
Single-View Hair Reconstruction using Convolutional Neural Networks
A deep learning-based method to generate full 3D hair geometry from an unconstrained image and demonstrates the effectiveness and robustness of the method on a wide range of challenging real Internet pictures, and shows reconstructed hair sequences from videos. Expand
HairNet: Single-View Hair Reconstruction Using Convolutional Neural Networks
A deep learning-based method to generate full 3D hair geometry from an unconstrained image and demonstrates the effectiveness and robustness of the method on a wide range of challenging real Internet pictures, and shows reconstructed hair sequences from videos. Expand
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss. Expand
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
This work thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improves each of them to derive an Enhanced SRGAN (ESRGAN), which achieves consistently better visual quality with more realistic and natural textures than SRGAN. Expand
Photographic Image Synthesis with Cascaded Refinement Networks
  • Qifeng Chen, V. Koltun
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
It is shown that photographic images can be synthesized from semantic layouts by a single feedforward network with appropriate structure, trained end-to-end with a direct regression objective. Expand
Learning Warped Guidance for Blind Face Restoration
Experiments show that the GFRNet not only performs favorably against the state-of-the-art image and face restoration methods, but also generates visually photo-realistic results on real degraded facial images. Expand
Image-to-Image Translation with Conditional Adversarial Networks
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Expand