[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122336-en":3,"doc-seo-122336-105":30,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122336,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Efficient encoding and decoding of voxelized models for machine learning-based applications","Point clouds are widely used as training data for machine-learning tasks in environmental modeling and precision agriculture, but raw storage and processing are hindered by high memory demands and sensor noise. Transforming data into voxel grids reduces noise effects and enables structured processing; however, voxelized geometry still strains on-device memory and low-latency pipelines. The document presents a compact encoding scheme with fast on-demand decoding, leveraging parallel GPU-friendly reconstruction. It uses multi-level context-aware prediction for voxel occupancy and residual coding via a pointerless sparse voxel octree (PSVO), achieving measurable storage reductions on tree datasets and diverse voxelized objects.","This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and content may change prior to final publication. Citation information: DOI 10. 1109/ACCESS.2025.3526202  \nDate of publication xxxx 00, 0000, date of current version xxxx 00, 0000.  \nDigital Object Identifier 10.1109/ACCESS.2023.0322000  \nEfficient encoding and decoding of voxelized models for machine learning-based applications  \nDAMJAN STRNAD 1, ŠTEFAN KOHEK1, BORUT ŽALIK1, LIBOR VÁŠA2, ANDREJ NERAT 1  \n1University of Maribor, Faculty of Electrical Engineering and Computer Science, Koroška cesta 46, 2000 Maribor, Slovenia 2University of West Bohemia, Faculty of Applied Sciences, Technická 8, 301 00 Plzeň, Czech Republic Corresponding author: Damjan Strnad (e-mail: [damjan.strnad@um.si](damjan.strnad@um.si)).  \nThis work was supported by the Slovenian Research and Innovation Agency under Grant P2-0041 and Grant J2-4458, and by the Czech Science Foundation under Grant 23-04622L.  \n ABSTRACT 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 apointerless 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.  \n INDEX TERMS Voxel grid; Feature prediction; Tree models; Prediction-based encoding; Key voxels; Residuals; Sparse voxel octree  \nI. INTRODUCTION  \nRemote sensing of environment, enabled by contemporary satellite, airborne, and terrestrial sensor platforms, has led to important advances in environmental monitoring [1]–[5], disaster detection and prevention [6]–[8], and precision agriculture [9]–[11] . It has also generated massive amounts of data at high level of detail. An example of this is detailed mapping of woody vegetation, which can be used to build machine learning-based decision support tools for optimizing management practices in forestry [12], [13] and precision horticulture [14],[15] . For instance, LiDAR-based scanning is becoming a viable solution for collecting structural information about individual trees (e.g., the tree branching exposed during its dormant period) in extensive orchards [16], which has compelling applications for both fruit growers and researchers in the field of phenology [17]–[19] . The obtained  \npoint clouds can be used for estimation of tree’s biomass, canopy size [20], [21], density [22], [23], and yield [24],[25] . By analyzing the changes detected in consecutive tree surveys, improved models of ","cbCaiinrKuZ5JKro","https://ap.wps.com/l/cbCaiinrKuZ5JKro","pdf",21949320,1,11,"English","en",105,"# Abstract\n# Introduction\n## Motivation: point clouds and voxelization\n## Challenge: storage and low-latency decoding\n## Proposed approach overview","[{\"question\":\"How does the method reduce storage size for voxelized models?\",\"answer\":\"It performs multi-level context-aware prediction of voxel occupancy and encodes the residual grid using a pointerless sparse voxel octree (PSVO), yielding reported storage reductions on both tree datasets and general voxelized objects.\"}]","Efficient encoding and decoding of voxelized models for machine learning-based applications | PDF",1785810088,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"efficient-encoding-and-decoding-of-voxelized-models-for-machine-learning-based-applications","",{"@graph":36,"@context":77},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/efficient-encoding-and-decoding-of-voxelized-models-for-machine-learning-based-applications/122336/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How does the method reduce storage size for voxelized models?","Question",{"text":75,"@type":76},"It performs multi-level context-aware prediction of voxel occupancy and encodes the residual grid using a pointerless sparse voxel octree (PSVO), yielding reported storage reductions on both tree datasets and general voxelized objects.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]