Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation

Isogawa, Mariko; Yuan, Ye; O’Toole, Matthew

doi:10.1109/cvpr42600.2020.00704

Cited by 59 publications

(28 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other sensors/sources: Besides using the aforementioned sensors, Isogawa et al [237] estimated 3D human pose from the 3D spatio-temporal histogram of photons captured by a non-line-of-sight (NLOS) imaging system. Tome et al [238] tackled the egocentric 3D pose estimation via a fish-eye camera.…”

Section: D Hpe From Other Sourcesmentioning

confidence: 99%

Deep Learning-Based Human Pose Estimation: A Survey

Zheng¹,

Wu²,

Yang³

et al. 2020

Preprint

View full text Add to dashboard Cite

Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. It has drawn increasing attention during the past decade and has been utilized in a wide range of applications including human-computer interaction, motion analysis, augmented reality, and virtual reality. Although the recently developed deep learning-based solutions have achieved high performance in human pose estimation, there still remain challenges due to insufficient training data, depth ambiguities, and occlusion. The goal of this survey paper is to provide a comprehensive review of recent deep learning-based solutions for both 2D and 3D pose estimation via a systematic analysis and comparison of these solutions based on their input data and inference procedures. More than 240 research papers since 2014 are covered in this survey. Furthermore, 2D and 3D human pose estimation datasets and evaluation metrics are included. Quantitative performance comparisons of the reviewed methods on popular datasets are summarized and discussed. Finally, the challenges involved, applications, and future research directions are concluded. We also provide a regularly updated project page: https://github.com/zczcwh/DL-HPE

show abstract

Section: D Hpe From Other Sourcesmentioning

confidence: 99%

Deep Learning-Based Human Pose Estimation: A Survey

Zheng¹,

Wu²,

Yang³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…At present, NLOS has been used in human pose classification through scattering media [115], three-dimensional multihuman pose estimation [116] and movement-based object tracking [117].…”

Section: F Non-line-of-sight Imagingmentioning

confidence: 99%

Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision

Suo¹,

Zhang²,

Gong³

et al. 2021

Preprint

View full text Add to dashboard Cite

Signal capture stands in the forefront to perceive and understand the environment and thus imaging plays the pivotal role in mobile vision. Recent explosive progresses in Artificial Intelligence (AI) have shown great potential to develop advanced mobile platforms with new imaging devices. Traditional imaging systems based on the "capturing images first and processing afterwards" mechanism cannot meet this unprecedented demand. Differently, Computational Imaging (CI) systems are designed to capture high-dimensional data in an encoded manner to provide more information for mobile vision systems. Thanks to AI, CI can now be used in real systems by integrating deep learning algorithms into the mobile vision platform to achieve the closed loop of intelligent acquisition, processing and decision making, thus leading to the next revolution of mobile vision. Starting from the history of mobile vision using digital cameras, this work first introduces the advances of CI in diverse applications and then conducts a comprehensive review of current research topics combining CI and AI. Motivated by the fact that most existing studies only loosely connect CI and AI (usually using AI to improve the performance of CI and only limited works have deeply connected them), in this work, we propose a framework to deeply integrate CI and AI by using the example of self-driving vehicles with high-speed communication, edge computing and traffic planning. Finally, we outlook the future of CI plus AI by investigating new materials, brain science and new computing techniques to shed light on new directions of mobile vision systems.

show abstract

“…Our approach addresses these drawbacks with a framework that integrates kinematic inference with RL-based character control, which runs in real-time, is compatible with advanced physics simulators, and has learning mechanisms that aim to match the output motion to the ground truth. Although prior work [64,65,16] has used RL to produce simple human locomotions from videos, these methods only learn policies that coarsely mimic limited types of motion instead of precisely tracking the motion presented in the video. In contrast, our approach can achieve accurate pose estimation by integrating images-based kinematic inference and RL-based character control with the proposed policy design and meta-PD control.…”

Section: Related Workmentioning

confidence: 99%