Pose-Guided High-Resolution Appearance Transfer via Progressive Training

08/27/2020
by   Ji Liu, et al.
0

We propose a novel pose-guided appearance transfer network for transferring a given reference appearance to a target pose in unprecedented image resolution (1024 * 1024), given respectively an image of the reference and target person. No 3D model is used. Instead, our network utilizes dense local descriptors including local perceptual loss and local discriminators to refine details, which is trained progressively in a coarse-to-fine manner to produce the high-resolution output to faithfully preserve complex appearance of garment textures and geometry, while hallucinating seamlessly the transferred appearances including those with dis-occlusion. Our progressive encoder-decoder architecture can learn the reference appearance inherent in the input image at multiple scales. Extensive experimental results on the Human3.6M dataset, the DeepFashion dataset, and our dataset collected from YouTube show that our model produces high-quality images, which can be further utilized in useful applications such as garment transfer between people and pose-guided human video generation.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 7

page 8

research
05/25/2017

Pose Guided Person Image Generation

This paper proposes the novel Pose Guided Person Generation Network (PG^...
research
02/14/2022

Multi-scale Attention Guided Pose Transfer

Pose transfer refers to the probabilistic image generation of a person w...
research
05/06/2022

CLIP-CLOP: CLIP-Guided Collage and Photomontage

The unabated mystique of large-scale neural networks, such as the CLIP d...
research
04/24/2021

Adaptive Appearance Rendering

We propose an approach to generate images of people given a desired appe...
research
08/16/2022

Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment

Editing hairstyle is unique and challenging due to the complexity and de...
research
05/21/2020

Wish You Were Here: Context-Aware Human Generation

We present a novel method for inserting objects, specifically humans, in...
research
08/10/2023

Neural Progressive Meshes

The recent proliferation of 3D content that can be consumed on hand-held...

Please sign up or login with your details

Forgot password? Click here to reset