activity
20182024
most citedLearning from THEODORE: A Synthetic Omnidirectional Top-View Indoor Dataset for Deep Transfer Learning

26 citations · 50 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV2024

NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images

Jingrui Yu, Dipankar Nandi, Roman Seidel +1

Human pose estimation (HPE) in the top-view using fisheye cameras presents a promising and innovative application domain. However, the availability of datasets capturing this viewp…

cs.CV2023

Applications of Deep Learning for Top-View Omnidirectional Imaging: A Survey

Jingrui Yu, Ana Cecilia Perez Grassi, Gangolf Hirtz

A large field-of-view fisheye camera allows for capturing a large area with minimal numbers of cameras when they are mounted on a high position facing downwards. This top-view omni…

cs.CV20231 cited

Human Pose Estimation in Monocular Omnidirectional Top-View Images

Jingrui Yu, Tobias Scheck, Roman Seidel +3

Human pose estimation (HPE) with convolutional neural networks (CNNs) for indoor monitoring is one of the major challenges in computer vision. In contrast to HPE in perspective vie…

cs.CV20228 cited

OmniPD: One-Step Person Detection in Top-View Omnidirectional Indoor Scenes

Jingrui Yu, Roman Seidel, Gangolf Hirtz

We propose a one-step person detector for topview omnidirectional indoor scenes based on convolutional neural networks (CNNs). While state of the art person detectors reach competi…

cs.CV2021

OmniFlow: Human Omnidirectional Optical Flow

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,…

cs.CV20208 cited

Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection

Tobias Scheck, Ana Perez Grassi, Gangolf Hirtz

Synthetic images are one of the most promising solutions to avoid high costs associated with generating annotated datasets to train supervised convolutional neural networks (CNN).…