paper-with-me

홈 › Papers

Real-time motion amplification on mobile devices

2022-06-16 · Henning U. Voss

A simple motion amplification algorithm suitable for real-time applications on mobile devices, including smartphones, is presented. It is based on motion enhancement by moving average differencing (MEMAD), a temporal high-pass filter for video streams. MEMAD can amplify small moving objects or subtle motion in larger objects. It is computationally sufficiently simple to be implemented in real time on smartphones. In the specific implementation as an Android phone app, MEMAD is demonstrated on examples chosen such as to motivate applications in the engineering, biological, and medical sciences.

📄 PDF Abstract BibTeX arXiv:2206.08422

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices

2024-07-08 · CVPR 2025 1 · Jianwen Jiang, Gaojie Lin, Zhengkun Rong, Chao Liang 외

Existing neural head avatars methods have achieved significant progress in the image quality and motion range of portrait animation. However, these methods neglect the computational overhead, and to the best of our knowl…

Image GenerationPortrait Animation

Instant 3D Object Tracking with Applications in Augmented Reality

2020-06-23 · Adel Ahmadyan, Tingbo Hou, Jianing Wei, Liangkai Zhang 외

Tracking object poses in 3D is a crucial building block for Augmented Reality applications. We propose an instant motion tracking system that tracks an object's pose in space (represented by its 3D bounding box) in real-…

3D Object TrackingCPUGPUObject Tracking

MobilePoser: Real-Time Full-Body Pose Estimation and 3D Human Translation from IMUs in Mobile Consumer Devices

2025-04-16 · Vasco Xu, Chenfeng Gao, Henry Hoffmann, Karan Ahuja

There has been a continued trend towards minimizing instrumentation for full-body motion capture, going from specialized rooms and equipment, to arrays of worn sensors and recently sparse inertial pose capture methods. H…

Pose EstimationTranslation

CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices

2024-12-17 · Andrei Znobishchev, Valerii Filev, Oleg Kudashev, Nikita Orlov 외

We present CompactFlowNet, the first real-time mobile neural network for optical flow prediction, which involves determining the displacement of each pixel in an initial frame relative to the corresponding pixel in a sub…

Action RecognitionMotion EstimationObject TrackingOptical Flow Estimation+3

Instant Motion Tracking and Its Applications to Augmented Reality

2019-07-16 · Jianing Wei, Genzhi Ye, Tyler Mullen, Matthias Grundmann 외

Augmented Reality (AR) brings immersive experiences to users. With recent advances in computer vision and mobile computing, AR has scaled across platforms, and has increased adoption in major products. One of the key cha…