DeepCap: Monocular Human Performance Capture Using Weak Supervision (CVPR 2020) - Oral
Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or did not recover dense space-time coherent geometry with frame-to-frame correspondences. We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multi-view supervision completely removing the need for training data with 3D ground truth annotations. The network architecture is based on two separate networks that disentangle the task into a pose estimation and a non-rigid surface deformation step. Extensive qualitative and quantitative evaluations show that our approach outperforms the state of the art in terms of quality and robustness.
M.Haberman, W. Xu, M. Zollhoefer, G.P.-Moll , C. Theobalt, DeepCap: Monocular Human Performance Capture Using Weak Supervision, CVPR 2020 (Oral)
Видео DeepCap: Monocular Human Performance Capture Using Weak Supervision (CVPR 2020) - Oral канала Christian Theobalt
M.Haberman, W. Xu, M. Zollhoefer, G.P.-Moll , C. Theobalt, DeepCap: Monocular Human Performance Capture Using Weak Supervision, CVPR 2020 (Oral)
Видео DeepCap: Monocular Human Performance Capture Using Weak Supervision (CVPR 2020) - Oral канала Christian Theobalt
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera - CVPR 2020 (Oral)](https://i.ytimg.com/vi/4uJCVSu9Lf4/default.jpg)
![Yann LeCun: "Energy-Based Self-Supervised Learning"](https://i.ytimg.com/vi/A7AnCvYDQrU/default.jpg)
![LiveCap: Real-time Human Performance Capture from Monocular Video (ACM TOG 2019)](https://i.ytimg.com/vi/HCC0z1WkQGc/default.jpg)
![This Robot Throws Objects with Amazing Precision](https://i.ytimg.com/vi/JJlSgm9OByM/default.jpg)
![XNect: Real-time Multi-person 3D Motion Capture With a Single RGB Camera (SIGGRAPH 2020)](https://i.ytimg.com/vi/tdxMo11KJGk/default.jpg)
![AI Learns to Park - Deep Reinforcement Learning](https://i.ytimg.com/vi/VMp6pq6_QjI/default.jpg)
![Deep Visual SLAM Frontends: SuperPoint, SuperGlue, and SuperMaps (#CVPR2020 Invited Talk)](https://i.ytimg.com/vi/u7Yo5EtOATQ/default.jpg)
![Full Performance Capture in Rokoko Studio - retarget in Blender + livestream to Unreal Engine](https://i.ytimg.com/vi/a0Mq_I_Lel8/default.jpg)
![Consistent Video Depth Estimation](https://i.ytimg.com/vi/5Tia2oblJAg/default.jpg)
![This AI Learned To Create Dynamic Photos! 🌁](https://i.ytimg.com/vi/Aq93TSau8GE/default.jpg)
![Computer Generates Human Faces](https://i.ytimg.com/vi/4VAkrUNLKSo/default.jpg)
![Deep Relightable Textures: Volumetric Performance Capture with Neural Rendering (SIGGRAPH Asia 2020)](https://i.ytimg.com/vi/A_Vw1F-yWzg/default.jpg)
![Theory and Systems for Weak Supervision (WWW 2020 BIG)](https://i.ytimg.com/vi/M7r5SGIxxpI/default.jpg)
![[CVPR'21 WAD] Keynote - Raquel Urtasun, Waabi/University of Toronto](https://i.ytimg.com/vi/PSZ2Px9PrHg/default.jpg)
![Retarget Motion Capture: Blender, Mixamo, and AutoRig Pro](https://i.ytimg.com/vi/gNCehuAEn_c/default.jpg)
![AI Learns To Compute Game Physics In Microseconds! ⚛️](https://i.ytimg.com/vi/atcKO15YVD8/default.jpg)
![Novel view synthesis of Dynamic Scenes with globally coherent depths from a monocular camera](https://i.ytimg.com/vi/kRKeoPkpPXM/default.jpg)
![Neural Monocular 3D Human Motion Capture With Physical Awareness (SIGGRAPH 2021)](https://i.ytimg.com/vi/8JhUjzFAMJI/default.jpg)
![Ken Burns Effect, Now In 3D!](https://i.ytimg.com/vi/FZZ9rpmVCqE/default.jpg)
![SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://i.ytimg.com/vi/MvPp-4GuspI/default.jpg)