1 code implementation • 6 Dec 2020 • Thanh Vu, Marc Eder, True Price, Jan-Michael Frahm
To address these constraints, we propose the Any-Width Network (AWN), an adjustable-width CNN architecture and associated training routine that allow for fine-grained control over speed and accuracy during inference.
1 code implementation • CVPR 2020 • Marc Eder, Mykhailo Shvets, John Lim, Jan-Michael Frahm
In this work, we propose "tangent images," a spherical image representation that facilitates transferable and scalable $360^\circ$ computer vision.
no code implementations • 1 Jul 2019 • Marc Eder, Pierre Moulon, Li Guan
In this work we present a method to train a plane-aware convolutional neural network for dense depth and surface normal estimation as well as plane boundaries from a single indoor $360^\circ$ image.
1 code implementation • 26 Jun 2019 • Marc Eder, True Price, Thanh Vu, Akash Bapat, Jan-Michael Frahm
We present a versatile formulation of the convolution operation that we term a "mapped convolution."
no code implementations • 21 May 2019 • Marc Eder, Jan-Michael Frahm
Applying convolutional neural networks to spherical images requires particular considerations.