Report
Learning from Abstract Images: on the Importance of Occlusion in a Minimalist Encoding of Human Poses
| العنوان: | Learning from Abstract Images: on the Importance of Occlusion in a Minimalist Encoding of Human Poses |
|---|---|
| المؤلفون: | Manzur, Saad, Hayes, Wayne |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | Existing 2D-to-3D pose lifting networks suffer from poor performance in cross-dataset benchmarks. Although the use of 2D keypoints joined by "stick-figure" limbs has shown promise as an intermediate step, stick-figures do not account for occlusion information that is often inherent in an image. In this paper, we propose a novel representation using opaque 3D limbs that preserves occlusion information while implicitly encoding joint locations. Crucially, when training on data with accurate three-dimensional keypoints and without part-maps, this representation allows training on abstract synthetic images, with occlusion, from as many synthetic viewpoints as desired. The result is a pose defined by limb angles rather than joint positions $\unicode{x2013}$ because poses are, in the real world, independent of cameras $\unicode{x2013}$ allowing us to predict poses that are completely independent of camera viewpoint. The result provides not only an improvement in same-dataset benchmarks, but a "quantum leap" in cross-dataset benchmarks. Comment: 10 pages |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2307.09893 |
| رقم الانضمام: | edsarx.2307.09893 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |