Publication detail

ICTree: Automatic Perceptual Metrics for Tree Models

POLÁŠEK, T. HRŮŠA, D. BENEŠ, B. ČADÍK, M.

Original Title

ICTree: Automatic Perceptual Metrics for Tree Models

Type

journal article in Web of Science

Language

English

Original 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.

Keywords

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

Authors

POLÁŠEK, T.; HRŮŠA, D.; BENEŠ, B.; ČADÍK, M.

Released

10. 12. 2021

ISBN

0730-0301

Periodical

ACM TRANSACTIONS ON GRAPHICS

Year of study

40

Number

6

State

United States of America

Pages from

1

Pages to

15

Pages count

15

URL

https://doi.org/10.1145/3478513.3480519

BibTex

@article{BUT168956,
  author="POLÁŠEK, T. and HRŮŠA, D. and BENEŠ, B. and ČADÍK, M.",
  title="ICTree: Automatic Perceptual Metrics for Tree Models",
  journal="ACM TRANSACTIONS ON GRAPHICS",
  year="2021",
  volume="40",
  number="6",
  pages="1--15",
  doi="10.1145/3478513.3480519",
  issn="0730-0301",
  url="https://doi.org/10.1145/3478513.3480519"
}