Publication Details

ICTree: Automatic Perceptual Metrics for Tree Models

POLÁŠEK Tomáš, HRŮŠA David, BENEŠ Bedřich and ČADÍK Martin. ICTree: Automatic Perceptual Metrics for Tree Models. ACM Transactions on Graphics (TOG), vol. 40, no. 6, 2021, pp. 1-15. ISSN 0730-0301. Available from: https://doi.org/10.1145/3478513.3480519
Czech title
ICTree: Automatická Percepční Metrika pro Modely Stromů
Type
journal article
Language
english
Authors
Polášek Tomáš, Ing. (DCGM FIT BUT)
Hrůša David (PU)
Beneš Bedřich, prof., Ph.D. (PU)
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

Evaluation & Perception, Natural Phenomena, User Studies, Generative 3D Modeling, Perception

Abstract

Many algorithms for synthetic tree generation exist, but the visual quality of the generated models is unknown. This problem is usually solved by performing limited user studies or by side-by-side comparison. We introduce an automated system for quality assessment of the tree model based on their perception. We conducted a user study in which over one million pairs of images were compared to collect subjective perceptual scores of generated trees. The perceptual score was used to train two neural-network-based predictors. A view independent ICTreeF uses the tree models geometric features that are easy to extract from any model. The second is ICTreeI that estimates the perceived visual quality of a tree from its image. Moreover, to provide an insight into the problem, we deduce intrinsic attributes and evaluate which features make trees look like real trees. In particular, we show that branching angles, length of branches, and widths are critical for perceived realism.

Published
2021
Pages
1-15
Journal
ACM Transactions on Graphics (TOG), vol. 40, no. 6, ISSN 0730-0301
Publisher
Association for Computing Machinery
DOI
UT WoS
000729846700035
EID Scopus
BibTeX
@ARTICLE{FITPUB12446,
   author = "Tom\'{a}\v{s} Pol\'{a}\v{s}ek and David Hr\r{u}\v{s}a and Bed\v{r}ich Bene\v{s} and Martin \v{C}ad\'{i}k",
   title = "ICTree: Automatic Perceptual Metrics for Tree Models",
   pages = "1--15",
   journal = "ACM Transactions on Graphics (TOG)",
   volume = 40,
   number = 6,
   year = 2021,
   ISSN = "0730-0301",
   doi = "10.1145/3478513.3480519",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12446"
}
Back to top