ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References
arXiv:2103.06747
Abstract
Capturing challenging human motions is critical for numerous applications, but it suffers from complex motion patterns and severe self-occlusion under the monocular setting. In this paper, we propose ChallenCap -- a template-based approach to capture challenging 3D human motions using a single RGB camera in a novel learning-and-optimization framework, with the aid of multi-modal references. We propose a hybrid motion inference stage with a generation network, which utilizes a temporal encoder-decoder to extract the motion details from the pair-wise sparse-view reference, as well as a motion discriminator to utilize the unpaired marker-based references to extract specific challenging motion characteristics in a data-driven manner. We further adopt a robust motion optimization stage to increase the tracking accuracy, by jointly utilizing the learned motion details from the supervised multi-modal references as well as the reliable motion hints from the input image reference. Extensive experiments on our new challenging motion dataset demonstrate the effectiveness and robustness of our approach to capture challenging human motions.
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Towards Accurate Markerless Human Shape and Pose Estimation over Time
- End-to-end Recovery of Human Shape and Pose
- Unite the People: Closing the Loop Between 3D and 2D Human Representations
- PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
- Monocular Total Capture: Posing Face, Body, and Hands in the Wild
- DeepCap: Monocular Human Performance Capture Using Weak Supervision
- DeepHuman: 3D Human Reconstruction from a Single Image
- Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
- Learning 3D Human Dynamics from Video
- Monocular Real-Time Volumetric Performance Capture
- EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera