Efficient multi-view training for 3D Gaussian Splatting

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Choi, Minhyuk, Kim, Injae, Kim, Hyunwoo J.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909651290816512
author Choi, Minhyuk
Kim, Injae
Kim, Hyunwoo J.
author_facet Choi, Minhyuk
Kim, Injae
Kim, Hyunwoo J.
contents 3D Gaussian Splatting (3DGS) has emerged as a preferred choice alongside Neural Radiance Fields (NeRF) in inverse rendering due to its superior rendering speed. Currently, the common approach in 3DGS is to utilize "single-view" mini-batch training, where only one image is processed per iteration, in contrast to NeRF's "multi-view" mini-batch training, which leverages multiple images. We observe that such single-view training can lead to suboptimal optimization due to increased variance in mini-batch stochastic gradients, highlighting the necessity for multi-view training. However, implementing multi-view training in 3DGS poses challenges. Simply rendering multiple images per iteration incurs considerable overhead and may result in suboptimal Gaussian densification due to its reliance on single-view assumptions. To address these issues, we modify the rasterization process to minimize the overhead associated with multi-view training and propose a 3D distance-aware D-SSIM loss and multi-view adaptive density control that better suits multi-view scenarios. Our experiments demonstrate that the proposed methods significantly enhance the performance of 3DGS and its variants, freeing 3DGS from the constraints of single-view training.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12727
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient multi-view training for 3D Gaussian Splatting
Choi, Minhyuk
Kim, Injae
Kim, Hyunwoo J.
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) has emerged as a preferred choice alongside Neural Radiance Fields (NeRF) in inverse rendering due to its superior rendering speed. Currently, the common approach in 3DGS is to utilize "single-view" mini-batch training, where only one image is processed per iteration, in contrast to NeRF's "multi-view" mini-batch training, which leverages multiple images. We observe that such single-view training can lead to suboptimal optimization due to increased variance in mini-batch stochastic gradients, highlighting the necessity for multi-view training. However, implementing multi-view training in 3DGS poses challenges. Simply rendering multiple images per iteration incurs considerable overhead and may result in suboptimal Gaussian densification due to its reliance on single-view assumptions. To address these issues, we modify the rasterization process to minimize the overhead associated with multi-view training and propose a 3D distance-aware D-SSIM loss and multi-view adaptive density control that better suits multi-view scenarios. Our experiments demonstrate that the proposed methods significantly enhance the performance of 3DGS and its variants, freeing 3DGS from the constraints of single-view training.
title Efficient multi-view training for 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.12727