Barbershop: GAN-based Image Compositing using Segmentation Masks

by   Peihao Zhu, et al.

Seamlessly blending features from multiple images is extremely challenging because of complex relationships in lighting, geometry, and partial occlusion which cause coupling between different parts of the image. Even though recent work on GANs enables synthesis of realistic hair or faces, it remains difficult to combine them into a single, coherent, and plausible image rather than a disjointed set of image patches. We present a novel solution to image blending, particularly for the problem of hairstyle transfer, based on GAN-inversion. We propose a novel latent space for image blending which is better at preserving detail and encoding spatial information, and propose a new GAN-embedding algorithm which is able to slightly modify images to conform to a common segmentation mask. Our novel representation enables the transfer of the visual properties from multiple reference images including specific details such as moles and wrinkles, and because we do image blending in a latent-space we are able to synthesize images that are coherent. Our approach avoids blending artifacts present in other approaches and finds a globally consistent image. Our results demonstrate a significant improvement over the current state of the art in a user study, with users preferring our blending solution over 95 percent of the time.


page 1

page 4

page 5

page 8

page 9

page 10

page 11


LOHO: Latent Optimization of Hairstyles via Orthogonalization

Hairstyle transfer is challenging due to hair structure differences in t...

Image Processing Using Multi-Code GAN Prior

Despite the success of Generative Adversarial Networks (GANs) in image s...

Robust GAN inversion

Recent advancements in real image editing have been attributed to the ex...

InsetGAN for Full-Body Image Generation

While GANs can produce photo-realistic images in ideal conditions for ce...

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

Existing GAN inversion and editing methods work well for aligned objects...

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE

Most existing methods for conditional image synthesis are only able to g...

3D Shape Generation with Grid-based Implicit Functions

Previous approaches to generate shapes in a 3D setting train a GAN on th...

Please sign up or login with your details

Forgot password? Click here to reset