Abstract This study presents a comparative evaluation of Neural Radiance Fields (NeRF)and 3D Gaussian Splatting (3DGS) for 3D reconstruction under various film-ing techniques. High-quality 3D models are essential in a range of applications,from forensic investigations to cultural heritage preservation, architecture, androbotics, where detail accuracy and minimal noise are critical. Leveraging con-tinuous video footage captured with a stabilized full-frame camera setup, thisresearch examines both algorithms across indoor and outdoor environments usingconsistent datasets. Key assessment criteria include reconstruction noise, detailpreservation, and processing time. The results reveal that while both approachesgenerate high-fidelity reconstructions, 3DGS consistently outperforms NeRFin computational efficiency and noise reduction. These insights provide valu-able guidance for selecting suitable reconstruction techniques across differentprofessional domains.
Rangelov et al. (Tue,) studied this question.