A primer on motion capture with deep learning: principles, pitfalls, and perspectives

A Mathis, S Schneider, J Lauer, MW Mathis - Neuron, 2020 - cell.com
Extracting behavioral measurements non-invasively from video is stymied by the fact that it is
a hard computational problem. Recent advances in deep learning have tremendously …

Deep learning for event-based vision: A comprehensive survey and benchmarks

X Zheng, Y Liu, Y Lu, T Hua, T Pan, W Zhang… - arxiv preprint arxiv …, 2023 - arxiv.org
Event cameras are bio-inspired sensors that capture the per-pixel intensity changes
asynchronously and produce event streams encoding the time, pixel position, and polarity …

Physical inertial poser (pip): Physics-aware real-time human motion tracking from sparse inertial sensors

X Yi, Y Zhou, M Habermann… - Proceedings of the …, 2022 - openaccess.thecvf.com
Motion capture from sparse inertial sensors has shown great potential compared to image-
based approaches since occlusions do not lead to a reduced tracking quality and the …

Humannerf: Efficiently generated human radiance field from sparse inputs

F Zhao, W Yang, J Zhang, P Lin… - Proceedings of the …, 2022 - openaccess.thecvf.com
Recent neural human representations can produce high-quality multi-view rendering but
require using dense multi-view inputs and costly training. They are hence largely limited to …

Intergen: Diffusion-based multi-human motion generation under complex interactions

H Liang, W Zhang, W Li, J Yu, L Xu - International Journal of Computer …, 2024 - Springer
We have recently seen tremendous progress in diffusion advances for generating realistic
human motions. Yet, they largely disregard the multi-human interactions. In this paper, we …

Physcap: Physically plausible monocular 3d motion capture in real time

S Shimada, V Golyanik, W Xu, C Theobalt - ACM Transactions on …, 2020 - dl.acm.org
Marker-less 3D human motion capture from a single colour camera has seen significant
progress. However, it is a very challenging and severely ill-posed problem. In consequence …

E2nerf: Event enhanced neural radiance fields from blurry images

Y Qi, L Zhu, Y Zhang, J Li - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRF) achieves impressive ren-dering performance by
learning volumetric 3D representation from several images of different views. However, it is …

Neural monocular 3d human motion capture with physical awareness

S Shimada, V Golyanik, W Xu, P Pérez… - ACM Transactions on …, 2021 - dl.acm.org
We present a new trainable system for physically plausible markerless 3D human motion
capture, which achieves state-of-the-art results in a broad range of challenging scenarios …

Eventnerf: Neural radiance fields from a single colour event camera

V Rudnev, M Elgharib, C Theobalt… - Proceedings of the …, 2023 - openaccess.thecvf.com
Asynchronously operating event cameras find many applications due to their high dynamic
range, vanishingly low motion blur, low latency and low data bandwidth. The field saw …

Evdistill: Asynchronous events to end-task learning via bidirectional reconstruction-guided cross-modal knowledge distillation

L Wang, Y Chae, SH Yoon, TK Kim… - Proceedings of the …, 2021 - openaccess.thecvf.com
Event cameras sense per-pixel intensity changes and produce asynchronous event streams
with high dynamic range and less motion blur, showing advantages over the conventional …