Your browser does not allow JavaScript!
JavaScript is necessary for the proper functioning of this website. Please enable JavaScript or use a modern browser.
Open Science Slovenia
Open Science
DiKUL
slv
|
eng
Search
Browse
New in RUL
About RUL
In numbers
Help
Sign in
Reflection probe interpolation for fast and accurate rendering of reflective materials
ID
Gojković, Katarina
(
Author
),
ID
Lesar, Žiga
(
Author
),
ID
Marolt, Matija
(
Author
)
PDF - Presentation file,
Download
(6,76 MB)
MD5: 15C1BE35EC9AF4E43129C67FBB777F17
Image galllery
Abstract
In this paper, we aim to improve rendering reflections using environment maps on moving reflective objects. Such scenarios require multiple reflection probes to be positioned at various locations in a scene. During rendering, the closest reflection probe is typically chosen as the environment map of a specific object, resulting in sharp transitions between the rendered reflections when the object moves around the scene. To solve this problem, we developed two convolutional neural networks that dynamically synthesize the best possible environment map at a given point in the scene. The first network generates an environment map from the coordinates of a given point through a decoder architecture. In the second approach, we triangulated the scene and captured environment maps at the triangle vertices – these represent reflection probes. The second network receives at the input three environment maps captured at the vertices of the triangle containing the query point, along with the distances between the query point and the vertices. Through an encoder-decoder architecture, the second network performs smart interpolation of the three environment maps. Both approaches are based on the phenomenon of overfitting, which made it necessary to train each network individually for specific scenes. Both networks are successful at predicting environment maps at arbitrary locations in the scene, even if these locations were not part of the training set. The accuracy of the predictions strongly depends on the complexity of the scene itself.
Language:
English
Keywords:
refection probes
,
interpolation
,
convolutional neural network
Work type:
Article
Typology:
1.01 - Original Scientific Article
Organization:
FRI - Faculty of Computer and Information Science
Year:
2024
Number of pages:
Str. 61-70
Numbering:
Vol. 32, no. 1/2
PID:
20.500.12556/RUL-160035
UDC:
004
ISSN on article:
1213-6964
DOI:
10.24132/JWSCG.2024.7
COBISS.SI-ID:
202681603
Publication date in RUL:
09.08.2024
Views:
105
Downloads:
20
Metadata:
Cite this work
Plain text
BibTeX
EndNote XML
EndNote/Refer
RIS
ABNT
ACM Ref
AMA
APA
Chicago 17th Author-Date
Harvard
IEEE
ISO 690
MLA
Vancouver
:
Copy citation
Share:
Record is a part of a journal
Title:
Journal of WSCG
Shortened title:
J. WSCG
Publisher:
Václav Skala-Union Agency
ISSN:
1213-6964
COBISS.SI-ID:
159710211
Licences
License:
CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:
http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:
The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Secondary language
Language:
Slovenian
Keywords:
odsevne sonde
,
interpolacija
,
konvolucijska nevronska mreža
Similar documents
Similar works from RUL:
Similar works from other Slovenian collections:
Back