{SelfPose}: {3D} Egocentric Pose Estimation from a Headset Mounted Camera
العنوان: | {SelfPose}: {3D} Egocentric Pose Estimation from a Headset Mounted Camera |
---|---|
المؤلفون: | Patrick Peluse, Denis Tome, Hernan Badino, Lourdes Agapito, Gerard Pons-Moll, Thiemo Alldieck, Fernando De la Torre |
المصدر: | IEEE Transactions on Pattern Analysis and Machine Intelligence |
بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2023. |
سنة النشر: | 2023 |
مصطلحات موضوعية: | FOS: Computer and information sciences, Ground truth, Monocular, Body shape, Computer science, Generalization, business.industry, Computer Vision and Pattern Recognition (cs.CV), Applied Mathematics, Headset, Perspective (graphical), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Computational Theory and Mathematics, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), 020201 artificial intelligence & image processing, Computer vision, Computer Vision and Pattern Recognition, Artificial intelligence, business, Pose, Software |
الوصف: | We present a solution to egocentric 3D body pose estimation from monocular images captured from downward looking fish-eye cameras installed on the rim of a head mounted VR device. This unusual viewpoint leads to images with unique visual appearance, with severe self-occlusions and perspective distortions that result in drastic differences in resolution between lower and upper body. We propose an encoder-decoder architecture with a novel multi-branch decoder designed to account for the varying uncertainty in 2D predictions. The quantitative evaluation, on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric approaches. To tackle the lack of labelled data we also introduced a large photo-realistic synthetic dataset. xR-EgoPose offers high quality renderings of people with diverse skintones, body shapes and clothing, performing a range of actions. Our experiments show that the high variability in our new synthetic training corpus leads to good generalization to real world footage and to state of theart results on real world datasets with ground truth. Moreover, an evaluation on the Human3.6M benchmark shows that the performance of our method is on par with top performing approaches on the more classic problem of 3D human pose from a third person viewpoint. 14 pages. arXiv admin note: substantial text overlap with arXiv:1907.10045 |
وصف الملف: | application/pdf |
تدمد: | 1939-3539 0162-8828 |
URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee9fad12aab2a199a7cc7abf72e57ef5 https://doi.org/10.1109/tpami.2020.3029700 |
حقوق: | OPEN |
رقم الأكسشن: | edsair.doi.dedup.....ee9fad12aab2a199a7cc7abf72e57ef5 |
قاعدة البيانات: | OpenAIRE |
تدمد: | 19393539 01628828 |
---|