Version 1
: Received: 14 January 2024 / Approved: 15 January 2024 / Online: 15 January 2024 (08:20:40 CET)
How to cite:
Chen, X.; Zheng, J.; He, L. STensoRRF:Tensorial able Relighting Radiance Field for Single-Tensor Scene Representation. Preprints2024, 2024011085. https://doi.org/10.20944/preprints202401.1085.v1
Chen, X.; Zheng, J.; He, L. STensoRRF:Tensorial able Relighting Radiance Field for Single-Tensor Scene Representation. Preprints 2024, 2024011085. https://doi.org/10.20944/preprints202401.1085.v1
Chen, X.; Zheng, J.; He, L. STensoRRF:Tensorial able Relighting Radiance Field for Single-Tensor Scene Representation. Preprints2024, 2024011085. https://doi.org/10.20944/preprints202401.1085.v1
APA Style
Chen, X., Zheng, J., & He, L. (2024). STensoRRF:Tensorial able Relighting Radiance Field for Single-Tensor Scene Representation. Preprints. https://doi.org/10.20944/preprints202401.1085.v1
Chicago/Turabian Style
Chen, X., JunHong Zheng and Lili He. 2024 "STensoRRF:Tensorial able Relighting Radiance Field for Single-Tensor Scene Representation" Preprints. https://doi.org/10.20944/preprints202401.1085.v1
Abstract
Reconstructing a 3D model of a scene from a set of multiple views poses a significant challenge in the field of computer vision. The advent of NeRF has marked a major breakthrough in this domain. However, there is a need to extend the capabilities of the NeRF model to enable editing tasks such as relighting and deformation, as well as to enhance its training efficiency. Neural reflectance fields introduce the concept of the reflectance equation into the NeRF framework to achieve relighting of the NeRF model. We leverage the TensoRF approach, which incorporates tensor decomposition and employs multiple tensors to store features, to expedite the training process of the NeRF model. Our novel method, called StensorR, combines the reflectance equation and tensor decomposition within the radiation field model framework. Differing from previous approaches, we employ a single tensor to store scene features and render the surface color of our scene using a simplified reflectance equation. This approach accelerates model convergence and enables relighting of the NeRF model. Experimental results demonstrate that our method achieves a 50% faster convergence rate compared to existing relighting radiation field models, while successfully enabling relighting and improving the quality of synthesized images from new viewpoints.
Keywords
computer vision; 3D Reconstructing; NeRF; relighting; the reflectance equation; tensor representation
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
