Enhancing NeRFs for High-Quality Indoor Video Generation: A Study on Parameterization and Recording Methods
Resumo
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.
Palavras-chave:
Neural Radiance Fields (NeRF), Technology-Task Fit (TTF), Parametrization, Recording Methods
Referências
Beatriz Albuquerque, Antonio Cunha, Leonardo Souza, Sean Siqueira, and Rodrigo Santos. 2024. Generating and Reviewing Programming Codes with Large Language Models:ASystematic Mapping Study. In Anais do XX Simpósio Brasileiro de Sistemas de Informação (Juiz de Fora/MG). SBC, Porto Alegre, RS, Brasil. [link]
Tafnes Silva Barbosa. 2024. Indoor Scene Parameterization. [link].
Jonathan T Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P Srinivasan. 2021. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In Proceedings of the IEEE/CVF international conference on computer vision. 5855–5864.
Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. 2022. Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5470–5479.
Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. 2023. Zip-nerf: Anti-aliased grid-based neural radiance fields. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 19697–19705.
Junyi Cao, Zhichao Li, Naiyan Wang, and Chao Ma. 2024. Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving.
Linsheng Chen, Guangrun Wang, Luchun Yuan, Keze Wang, Ken Deng, and Philip H.S. Torr. 2024. NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning.
Chenxi Lola Deng and Enzo Tartaglione. 2023. Compressing Explicit Voxel Grid Representations: fast NeRFs become also small. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE. DOI: 10.1109/wacv56688.2023.00129
Dale Goodhue. 1995. Understanding user evaluations of information systems. Management Science 41 (1995), 1827–1844. [link]
Dale Goodhue and Ronald L. Thompson. 1995. Task-Technology Fit and Individual Performance. MIS Q. 19 (1995), 213–236. [link]
Richard Hartley and Andrew Zisserman. 2003. Multiple view geometry in computer vision. Cambridge university press.
Siming He, Zach Osman, and Pratik Chaudhari. 2024. From NeRFs to Gaussian Splats, and Back. arXiv preprint arXiv:2405.09717 (2024).
Inwoo Hwang, Junho Kim, and Young Min Kim. 2023. Ev-NeRF: Event Based Neural Radiance Field. arXiv:2206.12455 [cs.CV] [link]
Kyungmin Jo, Gyumin Shim, Sanghun Jung, Soyoung Yang, and Jaegul Choo. 2021. CG-NeRF: Conditional Generative Neural Radiance Fields. arXiv:2112.03517 [cs.CV] [link]
Petr Kellnhofer, Abhimitra Meka, Michael Stengel, Christian Theobalt, Marcus Magnor, Hans-Peter Seidel, and Tobias Ritschel. 2021. Neural Lumigraph Rendering. IEEE Transactions on Visualization and Computer Graphics (2021).
Kai-En Lin, Lin Yen-Chen, Wei-Sheng Lai, Tsung-Yi Lin, Yi-Chang Shih, and Ravi Ramamoorthi. 2022. Vision Transformer for NeRF-Based View Synthesis from a Single Input Image. arXiv:2207.05736 [cs.CV] [link]
Lingjie Liu, Michael Zollhöfer, and Andreas Geiger. 2020. Neural sparse voxel fields. In Advances in Neural Information Processing Systems, Vol. 33. 15651–15663.
Yichen Liu, Benran Hu, Chi-Keung Tang, and Yu-Wing Tai. 2024. SANeRF-HQ: Segment Anything for NeRF in High Quality.
Li Ma, Xiaoyu Li, Jing Liao, Qi Zhang, XuanWang, JueWang, and Pedro V Sander. 2022. Deblur-nerf: Neural radiance fields from blurry images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12861–12870.
Davit Marikyan and Savvas Papagiannidis. 2023. Task-Technology Fit: A Review. In TheoryHub Book. TheoryHub.
Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi, Jonathan T. Barron, Alexey Dosovitskiy, and Daniel Duckworth. 2021. NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections. arXiv:2008.02268 [cs.CV] [link]
Ben Mildenhall, Pratul P. Srinivasan, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis.
Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65, 1 (2021), 99–106.
Thomas Müller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. CoRR abs/2201.05989 (2022). arXiv:2201.05989 [link]
Christian Reiser, Songyou Peng, Yiyi Liao, and Andreas Geiger. 2021. KiloNeRF: Speeding up neural radiance fields with thousands of tiny MLPs. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 14335–14345.
Weining Ren, Zihan Zhu, Boyang Sun, Jiaqi Chen, Marc Poliefeys, and Songyou Peng. 2024. NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild.
Azriel Rosenfeld. 1976. Digital picture processing. Academic press.
Johannes Lutz Schönberger and Jan-Michael Frahm. 2016. Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR).
Johannes Lutz Schönberger, Enliang Zheng, Marc Pollefeys, and Jan-Michael Frahm. 2016. Pixelwise View Selection for Unstructured Multi-View Stereo. In European Conference on Computer Vision (ECCV).
Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, Justin Kerr, Terrance Wang, Alexander Kristoffersen, Jake Austin, Kamyar Salahi, Abhik Ahuja, David McAllister, and Angjoo Kanazawa. 2023. Nerfstudio: A Modular Framework for Neural Radiance Field Development. In ACM SIGGRAPH 2023 Conference Proceedings (SIGGRAPH ’23).
Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600–612.
Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, and Victor Adrian Prisacariu. 2021. NeRF-: Neural Radiance Fields Without Known Camera Parameters. CoRR abs/2102.07064 (2021). arXiv:2102.07064 [link]
Guangtao Zhai and Xiongkuo Min. 2020. Perceptual image quality assessment: a survey. Science China Information Sciences 63 (2020), 1–52.
Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition. 586–595.
Dominik Zimmy, Joanna Waczynska, Tomasz Trzcinski, and Przemysław Spurek. 2024. Points2NeRF: Generating Neural Radiance Fields from 3D point cloud.
Tafnes Silva Barbosa. 2024. Indoor Scene Parameterization. [link].
Jonathan T Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P Srinivasan. 2021. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In Proceedings of the IEEE/CVF international conference on computer vision. 5855–5864.
Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. 2022. Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5470–5479.
Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. 2023. Zip-nerf: Anti-aliased grid-based neural radiance fields. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 19697–19705.
Junyi Cao, Zhichao Li, Naiyan Wang, and Chao Ma. 2024. Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving.
Linsheng Chen, Guangrun Wang, Luchun Yuan, Keze Wang, Ken Deng, and Philip H.S. Torr. 2024. NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning.
Chenxi Lola Deng and Enzo Tartaglione. 2023. Compressing Explicit Voxel Grid Representations: fast NeRFs become also small. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE. DOI: 10.1109/wacv56688.2023.00129
Dale Goodhue. 1995. Understanding user evaluations of information systems. Management Science 41 (1995), 1827–1844. [link]
Dale Goodhue and Ronald L. Thompson. 1995. Task-Technology Fit and Individual Performance. MIS Q. 19 (1995), 213–236. [link]
Richard Hartley and Andrew Zisserman. 2003. Multiple view geometry in computer vision. Cambridge university press.
Siming He, Zach Osman, and Pratik Chaudhari. 2024. From NeRFs to Gaussian Splats, and Back. arXiv preprint arXiv:2405.09717 (2024).
Inwoo Hwang, Junho Kim, and Young Min Kim. 2023. Ev-NeRF: Event Based Neural Radiance Field. arXiv:2206.12455 [cs.CV] [link]
Kyungmin Jo, Gyumin Shim, Sanghun Jung, Soyoung Yang, and Jaegul Choo. 2021. CG-NeRF: Conditional Generative Neural Radiance Fields. arXiv:2112.03517 [cs.CV] [link]
Petr Kellnhofer, Abhimitra Meka, Michael Stengel, Christian Theobalt, Marcus Magnor, Hans-Peter Seidel, and Tobias Ritschel. 2021. Neural Lumigraph Rendering. IEEE Transactions on Visualization and Computer Graphics (2021).
Kai-En Lin, Lin Yen-Chen, Wei-Sheng Lai, Tsung-Yi Lin, Yi-Chang Shih, and Ravi Ramamoorthi. 2022. Vision Transformer for NeRF-Based View Synthesis from a Single Input Image. arXiv:2207.05736 [cs.CV] [link]
Lingjie Liu, Michael Zollhöfer, and Andreas Geiger. 2020. Neural sparse voxel fields. In Advances in Neural Information Processing Systems, Vol. 33. 15651–15663.
Yichen Liu, Benran Hu, Chi-Keung Tang, and Yu-Wing Tai. 2024. SANeRF-HQ: Segment Anything for NeRF in High Quality.
Li Ma, Xiaoyu Li, Jing Liao, Qi Zhang, XuanWang, JueWang, and Pedro V Sander. 2022. Deblur-nerf: Neural radiance fields from blurry images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12861–12870.
Davit Marikyan and Savvas Papagiannidis. 2023. Task-Technology Fit: A Review. In TheoryHub Book. TheoryHub.
Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi, Jonathan T. Barron, Alexey Dosovitskiy, and Daniel Duckworth. 2021. NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections. arXiv:2008.02268 [cs.CV] [link]
Ben Mildenhall, Pratul P. Srinivasan, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis.
Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65, 1 (2021), 99–106.
Thomas Müller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. CoRR abs/2201.05989 (2022). arXiv:2201.05989 [link]
Christian Reiser, Songyou Peng, Yiyi Liao, and Andreas Geiger. 2021. KiloNeRF: Speeding up neural radiance fields with thousands of tiny MLPs. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 14335–14345.
Weining Ren, Zihan Zhu, Boyang Sun, Jiaqi Chen, Marc Poliefeys, and Songyou Peng. 2024. NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild.
Azriel Rosenfeld. 1976. Digital picture processing. Academic press.
Johannes Lutz Schönberger and Jan-Michael Frahm. 2016. Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR).
Johannes Lutz Schönberger, Enliang Zheng, Marc Pollefeys, and Jan-Michael Frahm. 2016. Pixelwise View Selection for Unstructured Multi-View Stereo. In European Conference on Computer Vision (ECCV).
Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, Justin Kerr, Terrance Wang, Alexander Kristoffersen, Jake Austin, Kamyar Salahi, Abhik Ahuja, David McAllister, and Angjoo Kanazawa. 2023. Nerfstudio: A Modular Framework for Neural Radiance Field Development. In ACM SIGGRAPH 2023 Conference Proceedings (SIGGRAPH ’23).
Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600–612.
Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, and Victor Adrian Prisacariu. 2021. NeRF-: Neural Radiance Fields Without Known Camera Parameters. CoRR abs/2102.07064 (2021). arXiv:2102.07064 [link]
Guangtao Zhai and Xiongkuo Min. 2020. Perceptual image quality assessment: a survey. Science China Information Sciences 63 (2020), 1–52.
Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition. 586–595.
Dominik Zimmy, Joanna Waczynska, Tomasz Trzcinski, and Przemysław Spurek. 2024. Points2NeRF: Generating Neural Radiance Fields from 3D point cloud.
Publicado
19/05/2025
Como Citar
BARBOSA, Tafnes Silva; RESENDE, Luis Henrique da S.; PEREIRA, Iuri Almeida; WIESE, Igor Scaliante; NAVES, Thiago França; SOARES, Telma Woerle de Lima; SOARES, Anderson da Silva.
Enhancing NeRFs for High-Quality Indoor Video Generation: A Study on Parameterization and Recording Methods. In: SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 21. , 2025, Recife/PE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 429-438.
DOI: https://doi.org/10.5753/sbsi.2025.246527.
