paper-with-me

Papers

Learning Human Optical Flow

2018-06-14 · Anurag Ranjan, Javier Romero, Michael J. Black

The optical flow of humans is well known to be useful for the analysis of human action. Given this, we devise an optical flow algorithm specifically for human motion and show that it is superior to generic flow methods. Designing a method by hand is impractical, so we develop a new training database of image sequences with ground truth optical flow. For this we use a 3D model of the human body and motion capture data to synthesize realistic flow fields. We then train a convolutional neural network to estimate human flow fields from pairs of images. Since many applications in human motion analysis depend on speed, and we anticipate mobile applications, we base our method on SpyNet with several modifications. We demonstrate that our trained network is more accurate than a wide range of top methods on held-out test data and that it generalizes well to real image sequences. When combined with a person detector/tracker, the approach provides a full solution to the problem of 2D human flow estimation. Both the code and the dataset are available for research.

📄 PDF Abstract BibTeX arXiv:1806.05666

Code (1)

anuragranj/humanflow 공식 구현 pytorch

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

Bootstrapping Human Optical Flow and Pose

2022-10-27 · Aritro Roy Arko, James J. Little, Kwang Moo Yi

We propose a bootstrapping framework to enhance human optical flow and pose. We show that, for videos involving humans in scenes, we can improve both the optical flow and the pose estimation quality of humans by consider…

Optical Flow EstimationPose Estimation

Learning Multi-Human Optical Flow

2019-10-24 · Anurag Ranjan, David T. Hoffmann, Dimitrios Tzionas, Siyu Tang 외

The optical flow of humans is well known to be useful for the analysis of human action. Recent optical flow methods focus on training deep networks to approach the problem. However, the training data used by them does no…

Optical Flow Estimation

Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data

2013-10-01 · Karla Brkić, Srđan Rašić, Axel Pinz, Siniša Šegvić 외

This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition. The STA descriptors are local histogram-based descriptors of space-time, suitable for building a …

Action RecognitionOptical Flow EstimationTemporal Action Localization

HuPerFlow: A Comprehensive Benchmark for Human vs. Machine Motion Estimation Comparison

2025-01-01 · CVPR 2025 1 · Yung-hao Yang, Zitang Sun, Taiki Fukiage, Shin'ya Nishida

As AI models are increasingly integrated into applications involving human interaction, understanding the alignment between human perception and machine vision has become essential. One example is the estimation of v…

Motion EstimationOptical Flow Estimation

OmniFlow: Human Omnidirectional Optical Flow

2021-04-16 · Roman Seidel, André Apitzsch, Gangolf Hirtz

Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to …

Optical Flow Estimation