image-generation

Pose Transfer

3260 papers • 126 benchmarks • 313 datasets

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

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in image-generation

Trend

Dataset

Best Model

Actions

Deep-Fashion

Market-1501

iDesigner

Libraries

i

Use these libraries to find image-generation models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

Composer: Creative and Controllable Image Synthesis with Composable Conditions

Jingren Zhou, Lianghua Huang, Yujun Shen, Deli Zhao, Di Chen, Yu Liu•Sun Feb 19 2023

This work offers a new generation paradigm that allows flexible control of the output image, such as spatial layout and palette, while maintaining the synthesis quality and model creativity, and serves as a general framework and facilitates a wide range of classical generative tasks without retraining.

358

Content

CelebAMask-HQ

ADE20K

SMPL

0

Paper Graph

Pose Guided Person Image Generation

L. Gool, Qianru Sun, B. Schiele, T. Tuytelaars, Liqian Ma, Xu Jia•Wed May 24 2017

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, is proposed.

872 0

Paper Graph

VirtualConductor: Music-driven Conducting Video Generation System

Zewen Li, Fan Liu, Delong Chen, Feng Xu•Tue Jul 27 2021

This work combines 3D animation rendering and a pose transfer model to synthesize conducting video from a single given user's image and proposes Audio Motion Correspondence Network and adversarial-perceptual learning to learn the cross-modal relationship and generate diverse, plausible, music-synchronized motion.

3 0

Paper Graph

Disentangled Person Image Generation

L. Gool, Qianru Sun, B. Schiele, Mario Fritz, Liqian Ma, Stamatios Georgoulis•Wed Dec 06 2017

A novel, two-stage reconstruction pipeline is proposed that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time and can manipulate the foreground, background and pose of the input image, and also sample new embedding features to generate targeted manipulations, that provide more control over the generation process.

451 0

Paper Graph

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

Jia-Bin Huang, Badour Albahar•Mon Sep 30 2019

This work addresses the problem of guided image-to-image translation where an input image is translated into another while respecting the constraints provided by an external, user-provided guidance image and presents a bi-directional feature transformation (bFT) scheme.

99 0

Paper Graph

Dense Intrinsic Appearance Flow for Human Pose Transfer

Chen Change Loy, Chen Huang, Yining Li•Tue Mar 26 2019

A novel approach for the task of human pose transfer, which aims at synthesizing a new image of a person from an input image of that person and a target pose, is presented, which addresses the issues of limited correspondences identified between keypoints only and invisible pixels due to self-occlusion.

200 0

Paper Graph

Progressive Pose Attention Transfer for Person Image Generation

X. Bai, Zhen Zhu, Baoguang Shi, Tengteng Huang, Miao Yu, Bofei Wang•Fri Apr 05 2019

A new generative adversarial network to the problem of pose transfer, i.e., transferring the pose of a given person to a target one, which can generate training images for person re-identification, alleviating data insufficiency.

345 0

Paper Graph

Controllable Person Image Synthesis With Attribute-Decomposed GAN

Z. Lian, Yifang Men, Yiming Mao, Yuning Jiang, Wei-Ying Ma•Thu Mar 26 2020

The Attribute-Decomposed GAN is introduced, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes provided in various source inputs and its superiority over the state of the art in pose transfer and its effectiveness in the brand-new task of component attribute transfer.

275 0

Paper Graph

XingGAN for Person Image Generation

N. Sebe, Philip H. S. Torr, Li Zhang, H. Tang, S. Bai•Thu Jul 16 2020

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 to mutually improve each other is proposed.

190 0

Paper Graph

Deformable GANs for Pose-Based Human Image Generation

N. Sebe, Aliaksandr Siarohin, Stéphane Lathuilière, E. Sangineto•Thu Dec 28 2017

This paper introduces deformable skip connections in the generator of the Generative Adversarial Network and proposes a nearest-neighbour loss instead of the common L1 and L2 losses in order to match the details of the generated image with the target image.

486 0

Paper Graph

Adding a benchmark result helps the community track progress.