← Search

Michael Schelling

2 accepted papers

2022

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

CVPR 2022poster

Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI). While recent research showed that 2D neural networks are able to outperform previous traditional State-of-the-Art (SOTA) methods on correcting ToF-Data, little research on learning-…

Cited by 14PDFcodeScholar
2022

Variance-Aware Weight Initialization for Point Convolutional Neural Networks

ECCV 2022poster

"Appropriate weight initialization has been of key importance to successfully train neural networks. Recently, batch normalization has diminished the role of weight initialization by simply normalizing each layer based on batch statistics. Unfortunately, batch normalization has several drawbacks whe…

Cited by 0SourcePDFScholar