Paper Info
Title
Virtual Rephotography: Novel View Prediction Error for 3D Reconstruction.
Abstract
The ultimate goal of many image-based modeling systems is to render photo-realistic novel views of a scene without visible artifacts. Existing evaluation metrics and benchmarks focus mainly on the geometric accuracy of the reconstructed model, which is, however, a poor predictor of visual accuracy. Furthermore, using only geometric accuracy by itself does not allow evaluating systems that either lack a geometric scene representation or utilize coarse proxy geometry. Examples include a light field and most image-based rendering systems. We 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. One key advantage of this approach is that it does not require ground truth geometry. This dramatically simplifies the creation of test datasets and benchmarks. It also allows us to evaluate the quality of an unknown scene during the acquisition and reconstruction process, which is useful for acquisition planning. We evaluate our approach on a range of methods, including standard geometry-plus-texture pipelines as well as image-based rendering techniques, compare it to existing geometry-based benchmarks, demonstrate its utility for a range of use cases, and present a new virtual rephotography-based benchmark for image-based modeling and rendering systems.
Year
DOI
Venue
2017
10.1145/3072959.3126787
ACM Transactions on Graphics (TOG)
Keywords
DocType
Volume
Image-based rendering,image-based modeling,3D reconstruction,multi-view stereo,novel view prediction error
Journal
36
Issue
ISSN
Citations 
4
0730-0301
7
PageRank 
References 
Authors
0.45
30
6
Name
Order
Citations
PageRank
Michael Waechter1775.44
Mate Beljan2110.87
Simon Fuhrmann31578.62
Nils Moehrle4713.22
johannes kopf5145865.35
Michael Goesele6100669.58