M
Michael Waechter
Researcher at Osaka University
Publications - 16
Citations - 616
Michael Waechter is an academic researcher from Osaka University. The author has contributed to research in topics: Photometric stereo & Structure from motion. The author has an hindex of 8, co-authored 16 publications receiving 434 citations. Previous affiliations of Michael Waechter include Technische Universität Darmstadt.
Papers
More filters
Book ChapterDOI
Let There Be Color! Large-Scale Texturing of 3D Reconstructions
TL;DR: This work presents the first comprehensive texturing framework for large-scale, real-world 3D reconstructions, and addresses most challenges occurring in such reconstructions: the large number of input images, their drastically varying properties such as image scale, (out-of-focus) blur, exposure variation, and occluders.
Journal ArticleDOI
MVE-An image-based reconstruction environment
TL;DR: The system provides a graphical user interface for visual inspection of the individual steps of the pipeline, i.e., the structure-from-motion result, multi-view stereo depth maps, and rendering of scenes and meshes, and it allows to reconstruct large datasets containing some detailed regions with much higher resolution than the rest of the scene.
Journal ArticleDOI
Rapid, detail-preserving image downscaling
TL;DR: An algorithm based on convolutional filters where input pixels contribute more to the output image the more their color deviates from their local neighborhood, which preserves visually important details is presented.
Journal ArticleDOI
Virtual Rephotography: Novel View Prediction Error for 3D Reconstruction
TL;DR: In this article, the authors propose a unified evaluation approach based on novel view prediction error that is able to analyze the visual quality of any method that can render novel views from input images.
Book ChapterDOI
What Is Learned in Deep Uncalibrated Photometric Stereo
TL;DR: The features learned by the proposed deep uncalibrated photometric stereo network strikingly resemble attached shadows, shadings, and specular highlights, which are known to provide useful clues in resolving the generalized bas-relief (GBR) ambiguity.