Evaluating 3D Reconstruction: A Side-by-Side Comparison of NeRF and Gaussian Splatting in Indoor and Outdoor Environments
Received: 14 December 2025 | Revised: 29 January 2026 | Accepted: 7 February 2026 | Online: 4 April 2026
Corresponding author: Dimitar Rangelov
Abstract
This study presents a comparative evaluation of Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) for 3D reconstruction in indoor and outdoor environments. High-quality 3D models are significant in a range of applications, from forensic investigations to cultural heritage preservation, architecture, and robotics, where detail accuracy and minimal noise are crucial. Leveraging continuous video footage captured with a stabilized full-frame camera setup, this research examines both algorithms across indoor and outdoor environments using consistent datasets. Key assessment criteria include reconstruction noise, detail preservation, and processing time. The results reveal that while both approaches generate high fidelity reconstructions, 3DGS outperforms NeRF in computational efficiency and noise reduction. These insights provide valuable guidance for selecting suitable reconstruction techniques across different professional domains. Due to the controlled scope and limited number of test scenes, the findings should be interpreted as indicative rather than statistically generalizable, serving primarily as a practical, application-oriented comparison.
Keywords:
3D reconstruction, Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), forensic imaging, radiance fieldsDownloads
References
E. M. Robinson, "Photogrammetry," in Crime Scene Photography, Amsterdam, Netherlands: Elsevier, 2016, pp. 411–453. DOI: https://doi.org/10.1016/B978-0-12-802764-6.00008-8
M. M. Houck, F. Crispino, and T. McAdam, "Photogrammetry and 3D Reconstruction," in The Science of Crime Scenes, Amsterdam, Netherlands: Elsevier, 2018, pp. 361–377. DOI: https://doi.org/10.1016/B978-0-12-849878-1.00027-2
Y. Feng, R. Wu, X. Liu, and L. Chen, "Three-Dimensional Reconstruction Based on Multiple Views of Structured Light Projectors and Point Cloud Registration Noise Removal for Fusion," Sensors, vol. 23, no. 21, Oct. 2023, Art. no. 8675. DOI: https://doi.org/10.3390/s23218675
I. Kalisperakis, L. Grammatikopoulos, E. Petsa, and G. Karras, "A Structured-Light Approach for the Reconstruction of Complex Objects," Geoinformatics FCE CTU, vol. 6, pp. 259–266, Dec. 2011. DOI: https://doi.org/10.14311/gi.6.32
B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, and R. Ng, "NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis," in Computer Vision – ECCV 2020, vol. 12346, A. Vedaldi, H. Bischof, T. Brox, and J.-M. Frahm, Eds. Cham: Springer International Publishing, 2020, pp. 405–421. DOI: https://doi.org/10.1007/978-3-030-58452-8_24
B. Kerbl, G. Kopanas, T. Leimkuehler, and G. Drettakis, "3D Gaussian Splatting for Real-Time Radiance Field Rendering," ACM Transactions on Graphics, vol. 42, no. 4, pp. 1–14, Aug. 2023. DOI: https://doi.org/10.1145/3592433
D. Rangelov, S. Waanders, K. Waanders, M. van Keulen, and R. Miltchev, "Impact of Data Capture Methods on 3D Reconstruction with Gaussian Splatting," Journal of Imaging, vol. 11, no. 2, Feb. 2025, Art. no. 65. DOI: https://doi.org/10.3390/jimaging11020065
D. Rangelov, S. Waanders, K. Waanders, M. van Keulen, and R. Miltchev, "Impact of Camera Settings on 3D Reconstruction Quality: Insights from NeRF and Gaussian Splatting," Sensors, vol. 24, no. 23, Nov. 2024, Art. no. 7594. DOI: https://doi.org/10.3390/s24237594
"Sony Alpha 7C Full-Frame Mirrorless Camera – Black | ILCE7C," Sony, Dec. 2024. https://electronics.sony.com/imaging/interchangeable-lens-cameras/all-interchangeable-lens-cameras/p/ilce7c-b.
"14mm F1.4 DG DN | Art | Lenses," SIGMA Corporation, Dec. 2024. https://www.sigma-global.com/en/lenses/a023_14_14/.
Jawset Postshot, version 0.4.1, Jawaset, Munich, Germany, Aug. 2024, [Online]. Available: https://www.jawset.com/.
S. J. Garbin, M. Kowalski, M. Johnson, J. Shotton, and J. Valentin, "FastNeRF: High-Fidelity Neural Rendering at 200FPS," in 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, Oct. 2021, pp. 14326–14335. DOI: https://doi.org/10.1109/ICCV48922.2021.01408
W. Bian, Z. Wang, K. Li, and J.-W. Bian, "NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior," in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, June 2023, pp. 4160–4169. DOI: https://doi.org/10.1109/CVPR52729.2023.00405
A. N. Sazaly, M. F. Mohd Ariff, and A. F. Razali, "3D Indoor Crime Scene Reconstruction from Micro UAV Photogrammetry Technique," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12020–12025, Dec. 2023. DOI: https://doi.org/10.48084/etasr.6260
A. Amamra, Y. Amara, K. Boumaza, and A. Benayad, "Crime Scene Reconstruction with RGB-D Sensors," in Federated Conference on Computer Science and Information Systems, Leipzig, Germany, Sept. 2019, pp. 391–396. DOI: https://doi.org/10.15439/2019F225
G. Galanakis et al., "A Study of 3D Digitisation Modalities for Crime Scene Investigation," Forensic Sciences, vol. 1, no. 2, pp. 56–85, July 2021. DOI: https://doi.org/10.3390/forensicsci1020008
Downloads
How to Cite
License
Copyright (c) 2026 Dimitar Rangelov, Sierd Waanders, Kars Waanders, Evgeni Genchev, Maurice van Keulen, Radoslav Miltchev
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
