Enhancing NeRFs for High-Quality Indoor Video Generation: A Study on Parameterization and Recording Methods

Context: The generation of 3D representations with Neural Radiance Fields (NeRFs) has revolutionized areas like virtual reality and space visualization, but video capture for these models lacks a systematic approach. Problem: Video capture for NeRFs is still based on trial and error, with few well-defined parameters, leading to inefficiencies, rework, and increased training times. This process is particularly challenging in indoor environments, where variations such as lighting and camera angles significantly impact the final quality of the reconstructions. Solution: This paper proposes a systematic approach to optimize video capture, evaluating parameters such as lighting, camera zoom, camera path, and height while presenting metrics to reduce visual artifacts. Information Systems Theory: The research is based on the Task-Technology Fit (TTF) Theory, which explores how technology should be adjusted to the specific needs of tasks, aiming to optimize video capture to enhance the quality of the generated models. Method: The research follows an experimental approach, using the Nerfstudio tool to test various parameters in a dataset of 48 videos. The analysis is quantitative, evaluating reconstruction quality metrics. Summary of Results: Lighting significantly impacts the quality of reconstructions, while changes in capture angles adversely affect the results. Contributions and Impact in the IS field: The research contributes a methodology to optimize video capture in NeRFs, driving technological advancements.