Learning Mesh Geometry Prediction
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43972289" target="_blank" >RIV/49777513:23520/24:43972289 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-031-63749-0_12" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-63749-0_12</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-63749-0_12" target="_blank" >10.1007/978-3-031-63749-0_12</a>
Alternative languages
Result language
angličtina
Original language name
Learning Mesh Geometry Prediction
Original language description
We propose a single-rate method for geometry compression of triangle meshes based on using a neural predictor to predict the encoded vertex positions using connectivity and an already known part of the geometry. The method is based on standard traversal-based methods but uses a neural predictor for prediction instead of a hand-crafted prediction scheme. The parameters of the neural predictor are learned on a dataset of existing triangle meshes. The method additionally includes an estimate of the prediction uncertainty, which is used to guide the encoding traversal of the mesh. The results of the proposed method are compared with a benchmark method on the ABC dataset using both mechanistic and perceptual metrics.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GF23-04622L" target="_blank" >GF23-04622L: Data compression paradigm based on omitting self-evident information - COMPROMISE</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Computational Science – ICCS 2024. Lecture Notes in Computer Science
ISBN
978-3-031-63748-3
ISSN
0302-9743
e-ISSN
1611-3349
Number of pages
15
Pages from-to
166-180
Publisher name
Springer Nature Switzerland
Place of publication
Cham
Event location
Málaga
Event date
Jul 2, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001279316700012