paper-with-me

홈 › Papers

Video Motion Capture from the Part Confidence Maps of Multi-Camera Images by Spatiotemporal Filtering Using the Human Skeletal Model

2019-12-09 · Takuya Ohashi, Yosuke Ikegami, Kazuki Yamamoto, Wataru Takano, Yoshihiko Nakamura

This paper discusses video motion capture, namely, 3D reconstruction of human motion from multi-camera images. After the Part Confidence Maps are computed from each camera image, the proposed spatiotemporal filter is applied to deliver the human motion data with accuracy and smoothness for human motion analysis. The spatiotemporal filter uses the human skeleton and mixes temporal smoothing in two-time inverse kinematics computations. The experimental results show that the mean per joint position error was 26.1mm for regular motions and 38.8mm for inverted motions.

📄 PDF Abstract BibTeX arXiv:1912.03880

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionPosition

Similar Papers 제목 키워드 기반

Monocular Total Capture: Posing Face, Body, and Hands in the Wild

2018-12-04 · CVPR 2019 6 · Donglai Xiang, Hanbyul Joo, Yaser Sheikh

We present the first method to capture the 3D total motion of a target person from a monocular view input. Given an image or a monocular video, our method reconstructs the motion from body, face, and fingers represented …

3D Human Pose EstimationHand Pose EstimationMonocular 3D Human Pose Estimation

SNM-VFI: Symmetric Nonlinear Motion-Guided Generative Video Frame Interpolation

2026-08-13 · Jisoo Jeong, Hong Cai, Jamie Menjay Lin, Hanno Ackermann 외 arxiv

We propose Symmetric Nonlinear Motion-guided Generative Video Frame Interpolation (SNM-VFI), a training-free framework for motion-controllable generative video frame interpolation with pre-trained optical flow and video …

Video Frame Interpolation

Disentangling Propagation and Generation for Video Prediction

2018-12-02 · ICCV 2019 10 · Hang Gao, Huazhe Xu, Qi-Zhi Cai, Ruth Wang 외

A dynamic scene has two types of elements: those that move fluidly and can be predicted from previous frames, and those which are disoccluded (exposed) and cannot be extrapolated. Prior approaches to video prediction typ…

Predict Future Video FramesPredictionVideo Prediction

LEO: Generative Latent Image Animator for Human Video Synthesis

2023-05-06 · Yaohui Wang, Xin Ma, Xinyuan Chen, Cunjian Chen 외

Spatio-temporal coherency is a major challenge in synthesizing high quality videos, particularly in synthesizing human videos that contain rich global and local deformations. To resolve this challenge, previous approache…

DisentanglementVideo Editing

MotionClone: Training-Free Motion Cloning for Controllable Video Generation

2024-06-08 · Pengyang Ling, Jiazi Bu, Pan Zhang, Xiaoyi Dong 외

Motion-based controllable video generation offers the potential for creating captivating visual content. Existing methods typically necessitate model training to encode particular motion cues or incorporate fine-tuning t…

DenoisingMotion GenerationMotion SynthesisText-to-Video Generation+1