paper-with-me

Papers

Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation

2025-03-25 · CVPR 2025 1 · Zhuoran Zhao, Linlin Yang, Pengzhan Sun, Pan Hui, Angela Yao

Recent synthetic 3D human datasets for the face, body, and hands have pushed the limits on photorealism. Face recognition and body pose estimation have achieved state-of-the-art performance using synthetic training data alone, but for the hand, there is still a large synthetic-to-real gap. This paper presents the first systematic study of the synthetic-to-real gap of 3D hand pose estimation. We analyze the gap and identify key components such as the forearm, image frequency statistics, hand pose, and object occlusions. To facilitate our analysis, we propose a data synthesis pipeline to synthesize high-quality data. We demonstrate that synthetic hand data can achieve the same level of accuracy as real data when integrating our identified components, paving the path to use synthetic data alone for hand pose estimation. Code and data are available at: https://github.com/delaprada/HandSynthesis.git.

📄 PDF Abstract BibTeX arXiv:2503.19307

Code (1)

delaprada/handsynthesis 공식 구현 pytorch

Tasks

3D Hand Pose EstimationFace RecognitionHand Pose EstimationPose Estimation

Similar Papers 제목 키워드 기반

Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehicles

2021-12-22 · Benjamin Kiefer, David Ott, Andreas Zell

Acquiring data to train deep learning-based object detectors on Unmanned Aerial Vehicles (UAVs) is expensive, time-consuming and may even be prohibited by law in specific environments. On the other hand, synthetic data i…

Objectobject-detectionObject Detection

H-GAN: the power of GANs in your Hands

2021-03-27 · Sergiu Oprea, Giorgos Karvounas, Pablo Martinez-Gonzalez, Nikolaos Kyriazis 외

We present HandGAN (H-GAN), a cycle-consistent adversarial learning approach implementing multi-scale perceptual discriminators. It is designed to translate synthetic images of hands to the real domain. Synthetic hands p…

Image-to-Image TranslationTone MappingTranslation

Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning

2021-06-15 · WeiQin Chuah, Ruwan Tennakoon, Alireza Bab-Hadiashar, David Suter

Learning-based stereo matching and depth estimation networks currently excel on public benchmarks with impressive results. However, state-of-the-art networks often fail to generalize from synthetic imagery to more challe…

Depth EstimationStereo Matching

SASMU: boost the performance of generalized recognition model using synthetic face dataset

2023-06-02 · Chia-Chun Chung, Pei-Chun Chang, Yong-Sheng Chen, Haoyuan He 외

Nowadays, deploying a robust face recognition product becomes easy with the development of face recognition techniques for decades. Not only profile image verification but also the state-of-the-art method can handle the …

Data AugmentationDomain GeneralizationFace RecognitionRobust Face Recognition

StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification

2020-04-25 · Sangrok Lee, Eunsoo Park, Hongsuk Yi, Sang Hun Lee

Vehicle re-identification aims to obtain the same vehicles from vehicle images. This is challenging but essential for analyzing and predicting traffic flow in the city. Although deep learning methods have achieved enormo…

Domain AdaptationVehicle Re-Identification