3D Modeling using Artificial Intelligence

This study investigates the potential of artificial intelligence in 3D modeling by comparing AI-generated models with human-created ones regarding user preferences, design complexity, and practical applications. Seven distinct model types, spanning categories like environment, creatures, and props, were selected for the study. Four AI-generated models were developed for each type using the tools Genie, ComfyUI, and 3DFY. The goal was to evaluate whether AI-generated models could match or surpass free-to-use human-made ones, considering factors like vertex and polygon counts and user preferences. Survey results revealed a general preference for human-made models, which garnered 41.7% of the votes despite representing only a quarter of the options. This was primarily attributed to their superior design coherence and visual consistency. However, AI tools like ComfyUI demonstrated potential, excelling in specific categories. Genie’s shield model received 41.2% of the votes compared to 35.3% for the human-made version. Similarly, AI models outperformed human-made counterparts in the fox and table categories, with ComfyUI (text prompt) achieving the highest user preference in both model types. Interestingly, higher vertex and polygon counts did not consistently correlate with user satisfaction, suggesting excessive detail may detract from a model’s appeal. The study also addresses ethical concerns surrounding AI's impact on creative industries and emphasizes the importance of sustainable practices in its implementation. While AI shows promise in 3D modeling, the findings underscore the irreplaceable role of human creativity in crafting models that resonate with users. This study contributes to the ongoing discourse on integrating AI into creative domains, hinting at a future where AI and human ingenuity collaborate to achieve remarkable results.

Publication Details

Journal
DiVA (Mälardalen University College)
Published
2025-01-01
Primary Topic
3D Surveying and Cultural Heritage
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

3D Modeling using Artificial Intelligence

DiVA (Mälardalen University College)
3D Surveying and Cultural Heritage
article

3D Modeling using Artificial Intelligence

article en

Abstract

This study investigates the potential of artificial intelligence in 3D modeling by comparing AI-generated models with human-created ones regarding user preferences, design complexity, and practical applications. Seven distinct model types, spanning categories like environment, creatures, and props, were selected for the study. Four AI-generated models were developed for each type using the tools Genie, ComfyUI, and 3DFY. The goal was to evaluate whether AI-generated models could match or surpass free-to-use human-made ones, considering factors like vertex and polygon counts and user preferences. Survey results revealed a general preference for human-made models, which garnered 41.7% of the votes despite representing only a quarter of the options. This was primarily attributed to their superior design coherence and visual consistency. However, AI tools like ComfyUI demonstrated potential, excelling in specific categories. Genie’s shield model received 41.2% of the votes compared to 35.3% for the human-made version. Similarly, AI models outperformed human-made counterparts in the fox and table categories, with ComfyUI (text prompt) achieving the highest user preference in both model types. Interestingly, higher vertex and polygon counts did not consistently correlate with user satisfaction, suggesting excessive detail may detract from a model’s appeal. The study also addresses ethical concerns surrounding AI's impact on creative industries and emphasizes the importance of sustainable practices in its implementation. While AI shows promise in 3D modeling, the findings underscore the irreplaceable role of human creativity in crafting models that resonate with users. This study contributes to the ongoing discourse on integrating AI into creative domains, hinting at a future where AI and human ingenuity collaborate to achieve remarkable results.

DiVA (Mälardalen University College)
Openalex Percentile: Top 38%
3D Surveying and Cultural Heritage
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.

3D Modeling using Artificial Intelligence · DiVA (Mälardalen University College) (2025) | TGRS Research Map | TGRS