Michael Waechter

About

Hi there (^-^)/

I'm Michael and my research interests include structure from motion, multi-view stereo, texturing of 3D reconstructions, optimization and many more.

どうぞよろしくお願い致します。

In the past I have been involved in the following research projects:

Discrete Search Photometric Stereo for Fast and Accurate Shape Estimation, Kenji Enomoto, Michael Waechter, Fumio Okura, Kiriakos N. Kutulakos, and Yasuyuki Matsushita, Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Shape and Albedo Recovery by Your Phone using Stereoscopic Flash and No-Flash Photography, Xu Cao, Michael Waechter, Boxin Shi, Ye Gao, Bo Zheng, Fumio Okura and Yasuyuki Matsushita, International Journal of Computer Vision (IJCV)

An Analysis of Sketched IRLS for Accelerated Sparse Residual Regression, Daichi Iwata, Michael Waechter and Yasuyuki Matsushita, European Conference on Computer Vision (ECCV) [supplemental material]
What is Learned in Deep Uncalibrated Photometric Stereo?, Guanying Chen, Michael Waechter, Boxin Shi, Kwan-Yee Kenneth Wong and Yasuyuki Matsushita, European Conference on Computer Vision (ECCV) [project page]
Deep near-light photometric stereo for spatially varying reflectances, Hiroaki Santo, Michael Waechter and Yasuyuki Matsushita, European Conference on Computer Vision (ECCV)
Photometric Stereo via Discrete Hypothesis-and-Test Search, Kenji Enomoto, Michael Waechter, Kyros Kutulakos and Yasuyuki Matsushita, Conference on Computer Vision and Pattern Recognition (CVPR)
Stereoscopic Flash and No-Flash Photography for Shape and Albedo Recovery, Xu Cao, Michael Waechter, Boxin Shi, Ye Gao, Bo Zheng and Yasuyuki Matsushita, Conference on Computer Vision and Pattern Recognition (CVPR)
Light Structure from Pin Motion: Geometric Point Light Source Calibration, Hiroaki Santo, Michael Waechter, Wen-Yan Lin, Yusuke Sugano and Yasuyuki Matsushita, International Journal of Computer Vision (IJCV) [project page]

Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-based Modeling, Hiroaki Santo, Michael Waechter, Masaki Samejima, Yusuke Sugano and Yasuyuki Matsushita, Oral at the European Conference on Computer Vision (ECCV) [supp. material] [project page] [Youtube]

Novel View Prediction Error as a Quality Metric for Image-Based Modeling and Rendering, Michael Waechter, PhD Thesis, Technische Universität Darmstadt
Virtual Rephotography: Novel View Prediction Error for 3D Reconstruction, Michael Waechter, Mate Beljan, Simon Fuhrmann, Nils Moehrle, Johannes Kopf and Michael Goesele, ACM Transactions on Graphics (presented at SIGGRAPH 2017), Vol. 36, No. 1, pp. 8:1-8:11 [supp. material] [project page]

Rapid, Detail-Preserving Image Downscaling, Nicolas Weber, Michael Waechter, Sandra C. Amend, Stefan Guthe and Michael Goesele, ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia) [project page]
A Fast, Massively Parallel Solver for Large, Irregular Pairwise Markov Random Fields, Daniel Thuerck, Michael Waechter, Sven Widmer, Max von Buelow, Patrick Seemann, Marc E. Pfetsch and Michael Goesele, High Performance Graphics (HPG) [supp. material] [project page]

MVE—An Image-based Reconstruction Environment, Simon Fuhrmann, Fabian Langguth, Nils Moehrle, Michael Waechter and Michael Goesele, Computers & Graphics, Vol. 53, pp. 44-53 [project page]

Using Graphics Processing Units to Investigate Molecular Coevolution, Michael Waechter, Kathrin Jaeger, Daniel Thuerck, Stephanie Weissgraeber, Sven Widmer, Michael Goesele and Kay Hamacher, Concurrency and Computation: Practice and Experience, Vol. 26, No. 6, pp. 1278-1296 [project page]
Let There Be Color! Large-Scale Texturing of 3D Reconstructions, Michael Waechter, Nils Moehrle and Michael Goesele, European Conference on Computer Vision (ECCV) [project page] [code]

Information-Theoretic Analysis of Molecular (Co)Evolution Using Graphics Processing Units, Michael Waechter, Kathrin Jaeger, Stephanie Weissgraeber, Sven Widmer, Michael Goesele and Kay Hamacher, International Workshop on Emerging Computational Methods for the Life Sciences (ECMLS) [project page]

Is Your Permutation Algorithm Unbiased for n ≠ 2^m?, Michael Waechter, Kay Hamacher, Franziska Hoffgaard, Sven Widmer and Michael Goesele, International Conference on Parallel Processing and Applied Mathematics (PPAM)