Reflectance Filtering

Institute Homepage

Institute Homepage Sign In

Back

Research Overview

Causal Representation Learning

Astronomy

Large Language Models and Causality

Kernel Methods and Probabilistic Modeling

Causality

Deep Learning and Generative Modeling

Robotics

Perceiving Systems Members Publications

Reflectance Filtering

Teaser — upper left: Input image; lower left: reflectance estimation of [Zoran et al. 2015]; upper right: guidance image inspired by [Bi et al. 2015], to refine reflectance prediction; lower right: final reflectance prediction after filtering the reflectance on the left using the guidance above to utilize the piecewise constant reflectance prior; For more details please see Figure 6 in the paper.

This is the project page for the paper "Reflectance Adaptive Filtering Improves Intrinsic Image Estimation" [], which appears at CVPR 2017 and can be found at https://arxiv.org/abs/1612.05062.

Code is available at https://github.com/tnestmeyer/reflectance-filtering.

If you find this useful, please consider citing

@inproceedings{nestmeyer2017reflectanceFiltering,
  title={Reflectance Adaptive Filtering Improves Intrinsic Image Estimation},
  author={Nestmeyer, Thomas and Gehler, Peter V},
  booktitle={Computer Vision and Pattern Recognition (CVPR)},
  year={2017}
}

Members

Perceiving Systems

Thomas Nestmeyer

Doctoral Researcher

Perceiving Systems

Peter Vincent Gehler

Research Group Leader

Publications

Perceiving Systems Conference Paper Reflectance Adaptive Filtering Improves Intrinsic Image Estimation Nestmeyer, T., Gehler, P. V. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), :1771-1780, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 () pre-print DOI BibTeX