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

09/13/2021
by   Badour AlBahar, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 4

page 6

page 8

page 9

page 10

11/28/2018

Coordinate-based Texture Inpainting for Pose-Guided Image Generation

We present a new deep learning approach to pose-guided resynthesis of hu...
09/30/2019

Unsupervised Pose Flow Learning for Pose Guided Synthesis

Pose guided synthesis aims to generate a new image in an arbitrary targe...
06/17/2021

Visual Correspondence Hallucination: Towards Geometric Reasoning

Given a pair of partially overlapping source and target images and a key...
01/11/2021

Neural Re-Rendering of Humans from a Single Image

Human re-rendering from a single image is a starkly under-constrained pr...
12/07/2020

Pose-Guided Human Animation from a Single Image in the Wild

We present a new pose transfer method for synthesizing a human animation...
04/01/2022

LASER: LAtent SpacE Rendering for 2D Visual Localization

We present LASER, an image-based Monte Carlo Localization (MCL) framewor...
04/20/2020

Pose Manipulation with Identity Preservation

This paper describes a new model which generates images in novel poses e...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.