Contact and Human Dynamics from Monocular Video (ECCV 2020)
Presented at the European Conference on Computer Vision (ECCV) 2020.
Project page: https://geometry.stanford.edu/projects/human-dynamics-eccv-2020
Abstract: Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetrating the ground and bodies leaning at extreme angles. In this paper, we present a physics-based method for inferring 3D human motion from video sequences that takes initial 2D and 3D pose estimates as input. We first estimate ground contact timings with a novel prediction network which is trained without hand-labeled data. A physics-based trajectory optimization then solves for a physically-plausible motion, based on the inputs. We show this process produces motions that are significantly more realistic than those from purely kinematic methods, substantially improving quantitative measures of both kinematic and dynamic plausibility. We demonstrate our method on character animation and pose estimation tasks on dynamic motions of dancing and sports with complex contact patterns.
Видео Contact and Human Dynamics from Monocular Video (ECCV 2020) канала Davis Winston Rempe
Project page: https://geometry.stanford.edu/projects/human-dynamics-eccv-2020
Abstract: Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetrating the ground and bodies leaning at extreme angles. In this paper, we present a physics-based method for inferring 3D human motion from video sequences that takes initial 2D and 3D pose estimates as input. We first estimate ground contact timings with a novel prediction network which is trained without hand-labeled data. A physics-based trajectory optimization then solves for a physically-plausible motion, based on the inputs. We show this process produces motions that are significantly more realistic than those from purely kinematic methods, substantially improving quantitative measures of both kinematic and dynamic plausibility. We demonstrate our method on character animation and pose estimation tasks on dynamic motions of dancing and sports with complex contact patterns.
Видео Contact and Human Dynamics from Monocular Video (ECCV 2020) канала Davis Winston Rempe
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Disambiguating Monocular Depth Estimation with a Single Transient (ECCV 2020)DeepFit : 3D Surface Fitting via Neural Network Weighted Least Squares (ECCV 2020 Oral)Monocular Real-Time Volumetric Performance Capture (ECCV 2020)DeepCap: Monocular Human Performance Capture Using Weak Supervision (CVPR 2020) - OralCVPR 2020: D3S - A Discriminative Single Shot Segmentation TrackerReal-time High-accuracy 3D Reconstruction with Consumer RGB-D CamerasDeep Volumetric Video From Very Sparse Multi-View Performance Capture (ECCV 2018)Few-Shot Video-to-Video Synthesis (NeurIPS 2019)Full-Time Monocular Road Detection Using Zero-Distribution Prior of Angle of Polarization (ECCV2020)How To Fix Forward Head Posture - 3 Easy Exercises (From a Chiropractor)World-Consistent Video-to-Video Synthesis (ECCV 2020)Collaborative Video Object Segmentation by Foreground-Background IntegrationSeated Exercises for Older AdultsThat's how Top Computer Vision Conference looks (ICCV 2019 Seoul, Korea)AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds [ ECCV 2020 ]VNect: real-time 3D human pose estimation with a single RGB camera (SIGGRAPH 2017 Presentation)[ECCV 2020] Foley Music: Learning to Generate Music from VideosECCV2020 Oral: Solving the Blind Perspective-n-Point Problem End-to-EndPointTriNet: Learned Triangulation of 3D Point Sets (ECCV 2020)SNE-RoadSeg (ECCV 2020)