Weakly-Supervised Optical Flow Estimation for Time-of-Flight

1 code implementation • 11 Oct 2022 • Michael Schelling, Pedro Hermosilla, Timo Ropinski

Indirect Time-of-Flight (iToF) cameras are a widespread type of 3D sensor, which perform multiple captures to obtain depth values of the captured scene.

Motion Compensation Optical Flow Estimation

Variance-Aware Weight Initialization for Point Convolutional Neural Networks

no code implementations • 7 Dec 2021 • Pedro Hermosilla, Michael Schelling, Tobias Ritschel, Timo Ropinski

Appropriate weight initialization has been of key importance to successfully train neural networks.

RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising

1 code implementation • CVPR 2022 • Michael Schelling, Pedro Hermosilla, Timo Ropinski

Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI).

Denoising

Enabling Viewpoint Learning through Dynamic Label Generation

1 code implementation • 10 Mar 2020 • Michael Schelling, Pedro Hermosilla, Pere-Pau Vazquez, Timo Ropinski

Optimal viewpoint prediction is an essential task in many computer graphics applications.