DeepAI AI Chat
Log In Sign Up

Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN

by   Badour AlBahar, et al.

We present an algorithm for re-rendering a person from a single image under arbitrary poses. Existing methods often have difficulties in hallucinating occluded contents photo-realistically while preserving the identity and fine details in the source image. We first learn to inpaint the correspondence field between the body surface texture and the source image with a human body symmetry prior. The inpainted correspondence field allows us to transfer/warp local features extracted from the source to the target view even under large pose changes. Directly mapping the warped local features to an RGB image using a simple CNN decoder often leads to visible artifacts. Thus, we extend the StyleGAN generator so that it takes pose as input (for controlling poses) and introduces a spatially varying modulation for the latent space using the warped local features (for controlling appearances). We show that our method compares favorably against the state-of-the-art algorithms in both quantitative evaluation and visual comparison.


page 1

page 2

page 4

page 6

page 8

page 9

page 10


Coordinate-based Texture Inpainting for Pose-Guided Image Generation

We present a new deep learning approach to pose-guided resynthesis of hu...

Unsupervised Pose Flow Learning for Pose Guided Synthesis

Pose guided synthesis aims to generate a new image in an arbitrary targe...

One-Shot Stylization for Full-Body Human Images

The goal of human stylization is to transfer full-body human photos to a...

Visual Correspondence Hallucination: Towards Geometric Reasoning

Given a pair of partially overlapping source and target images and a key...

VGFlow: Visibility guided Flow Network for Human Reposing

The task of human reposing involves generating a realistic image of a pe...

Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence Learning

In this paper, we target image-based person-to-person virtual try-on in ...

BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer

In this work, we propose a Robust, Efficient, and Component-specific mak...