paper-with-me

Papers

Pose-Based Sign Language Appearance Transfer

2024-10-17 · Amit Moryossef, Gerard Sant, Zifan Jiang

We introduce a method for transferring the signer's appearance in sign language skeletal poses while preserving the sign content. Using estimated poses, we transfer the appearance of one signer to another, maintaining natural movements and transitions. This approach improves pose-based rendering and sign stitching while obfuscating identity. Our experiments show that while the method reduces signer identification accuracy, it slightly harms sign recognition performance, highlighting a tradeoff between privacy and utility. Our code is available at https://github.com/sign-language-processing/pose-anonymization.

📄 PDF Abstract BibTeX arXiv:2410.13675

Code (1)

sign-language-processing/pose-anonymization 공식 구현

Tasks

Appearance Transfer

Similar Papers 제목 키워드 기반

Fine-grained Appearance Transfer with Diffusion Models

2023-11-27 · Yuteng Ye, Guanwen Li, Hang Zhou, Cai Jiale 외

Image-to-image translation (I2I), and particularly its subfield of appearance transfer, which seeks to alter the visual appearance between images while maintaining structural coherence, presents formidable challenges. De…

Appearance TransferImage-to-Image Translation

Text Guided Person Image Synthesis

2019-04-10 · CVPR 2019 6 · Xingran Zhou, Siyu Huang, Bin Li, Yingming Li 외

This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions. Our method can be boiled down to two stages: 1) text guided pose g…

AttributeImage GenerationVisual Question Answering (VQA)

GAC-GAN: A General Method for Appearance-Controllable Human Video Motion Transfer

2019-11-25 · Dongxu Wei, Xiaowei Xu, Haibin Shen, Kejie Huang

Human video motion transfer has a wide range of applications in multimedia, computer vision and graphics. Recently, due to the rapid development of Generative Adversarial Networks (GANs), there has been significant progr…

MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation

2020-11-18 · CVPR 2021 1 · Tianxiang Ma, Bo Peng, Wei Wang, Jing Dong

Pose-guided person image generation usually involves using paired source-target images to supervise the training, which significantly increases the data preparation effort and limits the application of the models. To dea…

Image GenerationPose TransferStyle Transfer

Pose-Guided High-Resolution Appearance Transfer via Progressive Training

2020-08-27 · Ji Liu, Heshan Liu, Mang-Tik Chiu, Yu-Wing Tai 외

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 …

Appearance TransferDecoderVideo GenerationVocal Bursts Intensity Prediction