Towards L-System Captioning for Tree Reconstruction
No Thumbnail Available
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
This work proposes a novel concept for tree and plant reconstruction by directly inferring a Lindenmayer-System (L-System) word representation from image data in an image captioning approach. We train a model end-to-end which is able to translate given images into L-System words as a description of the displayed tree. To prove this concept, we demonstrate the applicability on 2D tree topologies. Transferred to real image data, this novel idea could lead to more efficient, accurate and semantically meaningful tree and plant reconstruction without using error-prone point cloud extraction, and other processes usually utilized in tree reconstruction. Furthermore, this approach bypasses the need for a predefined L-System grammar and enables species-specific L-System inference without biological knowledge.
Description
CCS Concepts: Computing methodologies → Shape representations; Reconstruction; Shape analysis; Neural networks
@inproceedings{10.2312:egs.20231002,
booktitle = {Eurographics 2023 - Short Papers},
editor = {Babaei, Vahid and Skouras, Melina},
title = {{Towards L-System Captioning for Tree Reconstruction}},
author = {Magnusson, Jannes S. and Hilsmann, Anna and Eisert, Peter},
year = {2023},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {978-3-03868-209-7},
DOI = {10.2312/egs.20231002}
}