NeRF Is a Valuable Assistant for 3D Gaussian Splatting

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fang, Shuangkang, Shen, I-Chao, Igarashi, Takeo, Wang, Yufeng, Wang, ZeSheng, Yang, Yi, Ding, Wenrui, Zhou, Shuchang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911085391511552
author Fang, Shuangkang
Shen, I-Chao
Igarashi, Takeo
Wang, Yufeng
Wang, ZeSheng
Yang, Yi
Ding, Wenrui
Zhou, Shuchang
author_facet Fang, Shuangkang
Shen, I-Chao
Igarashi, Takeo
Wang, Yufeng
Wang, ZeSheng
Yang, Yi
Ding, Wenrui
Zhou, Shuchang
contents We introduce NeRF-GS, a novel framework that jointly optimizes Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). This framework leverages the inherent continuous spatial representation of NeRF to mitigate several limitations of 3DGS, including sensitivity to Gaussian initialization, limited spatial awareness, and weak inter-Gaussian correlations, thereby enhancing its performance. In NeRF-GS, we revisit the design of 3DGS and progressively align its spatial features with NeRF, enabling both representations to be optimized within the same scene through shared 3D spatial information. We further address the formal distinctions between the two approaches by optimizing residual vectors for both implicit features and Gaussian positions to enhance the personalized capabilities of 3DGS. Experimental results on benchmark datasets show that NeRF-GS surpasses existing methods and achieves state-of-the-art performance. This outcome confirms that NeRF and 3DGS are complementary rather than competing, offering new insights into hybrid approaches that combine 3DGS and NeRF for efficient 3D scene representation.
format Preprint
id arxiv_https___arxiv_org_abs_2507_23374
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeRF Is a Valuable Assistant for 3D Gaussian Splatting
Fang, Shuangkang
Shen, I-Chao
Igarashi, Takeo
Wang, Yufeng
Wang, ZeSheng
Yang, Yi
Ding, Wenrui
Zhou, Shuchang
Computer Vision and Pattern Recognition
We introduce NeRF-GS, a novel framework that jointly optimizes Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). This framework leverages the inherent continuous spatial representation of NeRF to mitigate several limitations of 3DGS, including sensitivity to Gaussian initialization, limited spatial awareness, and weak inter-Gaussian correlations, thereby enhancing its performance. In NeRF-GS, we revisit the design of 3DGS and progressively align its spatial features with NeRF, enabling both representations to be optimized within the same scene through shared 3D spatial information. We further address the formal distinctions between the two approaches by optimizing residual vectors for both implicit features and Gaussian positions to enhance the personalized capabilities of 3DGS. Experimental results on benchmark datasets show that NeRF-GS surpasses existing methods and achieves state-of-the-art performance. This outcome confirms that NeRF and 3DGS are complementary rather than competing, offering new insights into hybrid approaches that combine 3DGS and NeRF for efficient 3D scene representation.
title NeRF Is a Valuable Assistant for 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.23374