Neural Radiance Fields Based on Explicit Feature Matching and Scaled Dot-product Attention

Authors

• Mingwei Cao, School of Computer Science and Technology, Anhui University, Hefei 230601, China
• Fengna Wang, School of Computer Science and Technology, Anhui University, Hefei 230601, China
• Zilong Wang, School of Computer Science and Technology, Anhui University, Hefei 230601, China
• Haifeng Zhao, School of Computer Science and Technology, Anhui University, Hefei 230601, China

Abstract

Abstract: To address the problems that neural radiance fields(NeRF) are prone to artifacts and texture blurring in novel view synthesis under sparse view input and complex scenes, this paper proposed neural radiance fields based on explicit feature matching and scaled dot-product attention(EMD-NeRF). A multiscale feature extraction network was used to extract multi-scale feature information from the input sparse views. A fusion dot-product module was utilized to calculate view interaction information as a shared branch. Cosine similarity was adopted as a matching clue for similarity embedding volume rendering. A regularization loss function was used to enhance the quality of the scene color density field and improve the realism of the rendered new views. Experimental results on multiple open-source datasets verify the effectiveness of the proposed method.

Recommended Citation

Cao, Mingwei; Wang, Fengna; Wang, Zilong; and Zhao, Haifeng (2026) "Neural Radiance Fields Based on Explicit Feature Matching and Scaled Dot-product Attention," Journal of System Simulation: Vol. 38: Iss. 3, Article 3.
DOI: 10.16182/j.issn1004731x.joss.25-0568
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss3/3

First Page

572

Last Page

583

CLC

TP391.9

Recommended Citation

Cao Mingwei, Wang Fengna, Wang Zilong, et al. Neural Radiance Fields Based on Explicit Feature Matching and Scaled Dot-product Attention[J]. Journal of System Simulation, 2026, 38(3): 572-583.

Corresponding Author

Zhao Haifeng

DOI

10.16182/j.issn1004731x.joss.25-0568