Pose Transfer

41 papers with code • 6 benchmarks • 5 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Composer: Creative and Controllable Image Synthesis with Composable Conditions

damo-vilab/composer 20 Feb 2023

Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability.

Pose Guided Person Image Generation

sgoldyaev/DeepFashion.ADGAN NeurIPS 2017

This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose.

Progressive Pose Attention Transfer for Person Image Generation

tengteng95/Pose-Transfer CVPR 2019

This paper proposes a new generative adversarial network for pose transfer, i. e., transferring the pose of a given person to a target pose.

Controllable Person Image Synthesis with Attribute-Decomposed GAN

menyifang/adgan CVPR 2020

This paper introduces the Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e. g., pose, head, upper clothes and pants) provided in various source inputs.

XingGAN for Person Image Generation

Ha0Tang/XingGAN ECCV 2020

We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i. e., translating the pose of a given person to a desired one.

VirtualConductor: Music-driven Conducting Video Generation System

ChenDelong1999/VirtualConductor 28 Jul 2021

In this demo, we present VirtualConductor, a system that can generate conducting video from any given music and a single user's image.

Disentangled Person Image Generation

charliememory/Disentangled-Person-Image-Generation CVPR 2018

Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information.

Deformable GANs for Pose-based Human Image Generation

AliaksandrSiarohin/pose-gan CVPR 2018

Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose.

Dense Intrinsic Appearance Flow for Human Pose Transfer

ly015/intrinsic_flow CVPR 2019

Unlike existing methods, we propose to estimate dense and intrinsic 3D appearance flow to better guide the transfer of pixels between poses.

Guided Image-to-Image Translation with Bi-Directional Feature Transformation

vt-vl-lab/Guided-pix2pix ICCV 2019

We address the problem of guided image-to-image translation where we translate an input image into another while respecting the constraints provided by an external, user-provided guidance image.