Research Result Differences Between Manual Research and Using AI LLMs for Analyzing Popular 3D File Formats

A literature review has been conducted, helping outline some of the main peculiarities that exists within the 3D object file format domain. The difficulties that are present when working with different file formats in various fields have been noted – incompatibility issues, data loss, conversion difficulties, software wrappers, manufacturing industry standards and more. The problem of file format comparison has been defined – workflows are bogged down by the different output software tools use, expertise in different fields is a requirement, difficulties with conversion, complexity of file formats themselves and proprietary solutions, all lead to tremendous amount of manual work and technical knowledge required to keep track of differences between 3D file formats. As web sources for file format information can often become unreliable with time, new sources become available and analysis are constantly made, an argument has been made to try and use LLMs to alleviate some or most of the workload in file comparison. Such research necessitates a researcher to manually check all the output data of a model, in order to verify the correctness and accuracy of the used model. A methodology for the research process has been developed and implemented. Its main points include the definition of criteria for comparison, using manufacturing industry expert opinion to further verify the validity of the researcher and LLMs statements and the criteria itself, creation of comparison tables based on the criteria for all the chosen formats, short descriptions of the file formats themselves by the researcher and by the LLM and their comparison, as well as an analysis of file formats searchability on google trends. A comparison of binary data for some file formats is shown and described for further understanding of the issues with metadata and understanding proprietary 3D file formats. ISO standards for STEP ISO 10303-242:2022 and IGES, as well as their effects on the industry are briefly discussed. File formats that are discussed and compared: OBJ (Waveform obj, .obj); FBX (Filmbox, .fbx); glTF (GL Transmission Format, .glTF, .glb); USD/USDZ (Universal Scene Descriptor, .usd, .usdz); BLEND (Blender file format, .blend); AMF (Additive Manufacturing, .amf); STL (Stereolithography, .stl); 3DS (3D Studio Scene, .3ds); IGES (Initial Graphics Exchange Specification, .igs, .iges); STEP (Standard for the Exchange for Product Data, .stp, .step); DAE, Collada (Digital Asset Exchange File, .dae).

Authors

Institutions

Publication Details

Journal
TEM Journal
Published
2024-11-27
DOI
https://doi.org/10.18421/tem134-02
Citations
6
Primary Topic
Image Processing and 3D Reconstruction
Type
article
Field-Weighted Citation Impact
1.50
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Research Result Differences Between Manual Research and Using AI LLMs for Analyzing Popular 3D File Formats

Galina Ivanova, Vasil Kozov, A. L. Ivanov
6 citations
TEM Journal
Image Processing and 3D Reconstruction
1.50
article

Research Result Differences Between Manual Research and Using AI LLMs for Analyzing Popular 3D File Formats

Galina Ivanova, Vasil Kozov, A. L. Ivanov
article en
6 citations

Abstract

A literature review has been conducted, helping outline some of the main peculiarities that exists within the 3D object file format domain. The difficulties that are present when working with different file formats in various fields have been noted – incompatibility issues, data loss, conversion difficulties, software wrappers, manufacturing industry standards and more. The problem of file format comparison has been defined – workflows are bogged down by the different output software tools use, expertise in different fields is a requirement, difficulties with conversion, complexity of file formats themselves and proprietary solutions, all lead to tremendous amount of manual work and technical knowledge required to keep track of differences between 3D file formats. As web sources for file format information can often become unreliable with time, new sources become available and analysis are constantly made, an argument has been made to try and use LLMs to alleviate some or most of the workload in file comparison. Such research necessitates a researcher to manually check all the output data of a model, in order to verify the correctness and accuracy of the used model. A methodology for the research process has been developed and implemented. Its main points include the definition of criteria for comparison, using manufacturing industry expert opinion to further verify the validity of the researcher and LLMs statements and the criteria itself, creation of comparison tables based on the criteria for all the chosen formats, short descriptions of the file formats themselves by the researcher and by the LLM and their comparison, as well as an analysis of file formats searchability on google trends. A comparison of binary data for some file formats is shown and described for further understanding of the issues with metadata and understanding proprietary 3D file formats. ISO standards for STEP ISO 10303-242:2022 and IGES, as well as their effects on the industry are briefly discussed. File formats that are discussed and compared: OBJ (Waveform obj, .obj); FBX (Filmbox, .fbx); glTF (GL Transmission Format, .glTF, .glb); USD/USDZ (Universal Scene Descriptor, .usd, .usdz); BLEND (Blender file format, .blend); AMF (Additive Manufacturing, .amf); STL (Stereolithography, .stl); 3DS (3D Studio Scene, .3ds); IGES (Initial Graphics Exchange Specification, .igs, .iges); STEP (Standard for the Exchange for Product Data, .stp, .step); DAE, Collada (Digital Asset Exchange File, .dae).

TEM Journal
Angel Kanchev University of Ruse (BG)
Industry, innovation and infrastructure
Openalex Percentile: Top 16%
Image Processing and 3D Reconstruction
1.50
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.