Search Results for author: Konrad Groh

Found 3 papers, 1 papers with code

Intrinsic Image Decomposition Using Point Cloud Representation

1 code implementation20 Jul 2023 Xiaoyan Xing, Konrad Groh, Sezer Karaoglu, Theo Gevers

The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties).

Intrinsic Image Decomposition

Overfitting Detection of Deep Neural Networks without a Hold Out Set

no code implementations ICLR 2019 Konrad Groh

Here we challenge this rationale and investigate criteria for overfitting without using a holdout data set.

On the Construction and Evaluation of Color Invariant Networks

no code implementations ICLR 2018 Konrad Groh

This is an empirical paper which constructs color invariant networks and evaluates their performances on a realistic data set.

Cannot find the paper you are looking for? You can Submit a new open access paper.