| | SLO | ENG | Piškotki in zasebnost

Večja pisava | Manjša pisava
Prva stran > Izpis gradiva

Izpis gradiva Pomoč

Naslov:Efficient encoding and decoding of voxelized models for machine learning-based applications
Avtorji:ID Strnad, Damjan (Avtor)
ID Kohek, Štefan (Avtor)
ID Žalik, Borut (Avtor)
ID Váša, Libor (Avtor)
ID Nerat, Andrej (Avtor)
Datoteke:.pdf Efficient_encoding_and_decoding_of_voxelized_models_for_machine_learning-based_applications.pdf (20,93 MB)
MD5: 5827A8FEB767966A4E1E5175EA79C0A3
 
Jezik:Angleški jezik
Vrsta gradiva:Članek v reviji
Tipologija:1.01 - Izvirni znanstveni članek
Organizacija:FERI - Fakulteta za elektrotehniko, računalništvo in informatiko
Opis:Point clouds have become a popular training data for many practical applications of machine learning in the fields of environmental modeling and precision agriculture. In order to reduce high space requirements and the effect of noise in the data, point clouds are often transformed to a structured representation such as a voxel grid. Storing, transmitting and consuming voxelized geometry, however, remains a challenging problem for machine learning pipelines running on devices with limited amount of on-chip memory with low access latency. A viable solution is to store the data in a compact encoded format, and perform on-the-fly decoding when it is needed for processing. Such on-demand expansion must be fast in order to avoid introducing substantial additional delay to the pipeline. This can be achieved by parallel decoding, which is particularly suitable for massively parallel architecture of GPUs on which the majority of machine learning is currently executed. In this paper, we present such method for efficient and parallelizable encoding/decoding of voxelized geometry. The method employs multi-level context-aware prediction of voxel occupancy based on the extracted binary feature prediction table, and encodes the residual grid with a pointerless sparse voxel octree (PSVO). We particularly focused on encoding the datasets of voxelized trees, obtained from both synthetic tree models and LiDAR point clouds of real trees. The method achieved 15.6% and 12.8% reduction of storage size with respect to plain PSVO on synthetic and real dataset, respectively. We also tested the method on a general set of diverse voxelized objects, where an average 11% improvement of storage space was achieved.
Ključne besede:voxel grid, feature prediction, tree models, prediction-based encoding, key voxels, residuals, sparse voxel octree
Status publikacije:Objavljeno
Verzija publikacije:Objavljena publikacija
Datum objave:06.01.2025
Založnik:IEEE ACCESS
Leto izida:2025
Št. strani:11 str.
PID:20.500.12556/DKUM-91506 Novo okno
UDK:004.9
COBISS.SI-ID:221454083 Novo okno
DOI:10.1109/ACCESS.2025.3526202 Novo okno
ISSN pri članku:2169-3536
Datum objave v DKUM:09.01.2025
Število ogledov:0
Število prenosov:5
Metapodatki:XML DC-XML DC-RDF
Področja:Ostalo
:
STRNAD, Damjan, KOHEK, Štefan, ŽALIK, Borut, VÁŠA, Libor in NERAT, Andrej, 2025, Efficient encoding and decoding of voxelized models for machine learning-based applications. IEEE access [na spletu]. 2025. [Dostopano 18 april 2025]. DOI 10.1109/ACCESS.2025.3526202. Pridobljeno s: https://dk.um.si/IzpisGradiva.php?lang=slv&id=91506
Kopiraj citat
  
Skupna ocena:
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
(0 glasov)
Vaša ocena:Ocenjevanje je dovoljeno samo prijavljenim uporabnikom.
Objavi na:Bookmark and Share


Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše podrobnosti ali sproži prenos.

Gradivo je del revije

Naslov:IEEE access
Založnik:Institute of Electrical and Electronics Engineers
ISSN:2169-3536
COBISS.SI-ID:519839513 Novo okno

Gradivo je financirano iz projekta

Financer:ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
Številka projekta:P2-0041-2020
Naslov:Računalniški sistemi, metodologije in inteligentne storitve
Financer:ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
Številka projekta:J2-4458-2022
Naslov:Paradigma stiskanja podatkov z odstranjevanjem obnovljivih informacij
Financer:Drugi - Drug financer ali več financerjev
Številka projekta:23-04622L

Licence

Licenca:CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
Povezava:http://creativecommons.org/licenses/by/4.0/deed.sl
Opis:To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

Jezik:Slovenski jezik
Ključne besede:računalniške mreže, drevesni modeli, kodiranje na podlagi predvidevanja


Komentarji

Dodaj komentar

Za komentiranje se morate prijaviti.

Komentarji (0)
0 - 0 / 0
 
Ni komentarjev!

Nazaj
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici