no code implementations • 28 Feb 2024 • Jingrui Yu, Dipankar Nandi, Roman Seidel, Gangolf Hirtz
Through this pipeline, we create a novel dataset NToP570K (NeRF-powered Top-view human Pose dataset for fisheye cameras with over 570 thousand images), and conduct an extensive evaluation of its efficacy in enhancing neural networks for 2D and 3D top-view human pose estimation.
no code implementations • 17 Apr 2023 • Jingrui Yu, Tobias Scheck, Roman Seidel, Yukti Adya, Dipankar Nandi, Gangolf Hirtz
In our work we propose a new dataset for training and evaluation of CNNs for the task of keypoint detection in omnidirectional images.
no code implementations • 14 Apr 2022 • Jingrui Yu, Roman Seidel, Gangolf Hirtz
To enhance the fine-tuning process, we add a subset of HDA Person dataset and a subset of PIROPOdatabase and reduce the number of perspective images to PASCAL VOC07.
no code implementations • 16 Apr 2021 • Roman Seidel, André Apitzsch, Gangolf Hirtz
To verify the data for training volumetric correspondence networks for optical flow estimation we train different subsets of the data and test on OmniFlow with and without Test-Time-Augmentation.
no code implementations • 11 Nov 2020 • Tobias Scheck, Roman Seidel, Gangolf Hirtz
Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs).
no code implementations • 22 May 2018 • Roman Seidel, André Apitzsch, Gangolf Hirtz
For this purpose we fine-tuned the soft non-maximum suppression with Gaussian smoothing.
1 code implementation • 24 Apr 2018 • André Apitzsch, Roman Seidel, Gangolf Hirtz
We investigate CNN architectures to determine high motion variations caused by the geometry of fish-eye images.