Saved in:
Bibliographic Details
Main Authors: Li, Tianyu, Qiu, Yihang, Wu, Zhenhua, Lindström, Carl, Su, Peng, Nießner, Matthias, Li, Hongyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.12552
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916659370917888
author Li, Tianyu
Qiu, Yihang
Wu, Zhenhua
Lindström, Carl
Su, Peng
Nießner, Matthias
Li, Hongyang
author_facet Li, Tianyu
Qiu, Yihang
Wu, Zhenhua
Lindström, Carl
Su, Peng
Nießner, Matthias
Li, Hongyang
contents Multi-traversal data, commonly collected through daily commutes or by self-driving fleets, provides multiple viewpoints for scene reconstruction within a road block. This data offers significant potential for high-quality novel view synthesis, which is crucial for applications such as autonomous vehicle simulators. However, inherent challenges in multi-traversal data often result in suboptimal reconstruction quality, including variations in appearance and the presence of dynamic objects. To address these issues, we propose Multi-Traversal Gaussian Splatting (MTGS), a novel approach that reconstructs high-quality driving scenes from arbitrarily collected multi-traversal data by modeling a shared static geometry while separately handling dynamic elements and appearance variations. Our method employs a multi-traversal dynamic scene graph with a shared static node and traversal-specific dynamic nodes, complemented by color correction nodes with learnable spherical harmonics coefficient residuals. This approach enables high-fidelity novel view synthesis and provides flexibility to navigate any viewpoint. We conduct extensive experiments on a large-scale driving dataset, nuPlan, with multi-traversal data. Our results demonstrate that MTGS improves LPIPS by 23.5% and geometry accuracy by 46.3% compared to single-traversal baselines. The code and data would be available to the public.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12552
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MTGS: Multi-Traversal Gaussian Splatting
Li, Tianyu
Qiu, Yihang
Wu, Zhenhua
Lindström, Carl
Su, Peng
Nießner, Matthias
Li, Hongyang
Computer Vision and Pattern Recognition
Graphics
Multi-traversal data, commonly collected through daily commutes or by self-driving fleets, provides multiple viewpoints for scene reconstruction within a road block. This data offers significant potential for high-quality novel view synthesis, which is crucial for applications such as autonomous vehicle simulators. However, inherent challenges in multi-traversal data often result in suboptimal reconstruction quality, including variations in appearance and the presence of dynamic objects. To address these issues, we propose Multi-Traversal Gaussian Splatting (MTGS), a novel approach that reconstructs high-quality driving scenes from arbitrarily collected multi-traversal data by modeling a shared static geometry while separately handling dynamic elements and appearance variations. Our method employs a multi-traversal dynamic scene graph with a shared static node and traversal-specific dynamic nodes, complemented by color correction nodes with learnable spherical harmonics coefficient residuals. This approach enables high-fidelity novel view synthesis and provides flexibility to navigate any viewpoint. We conduct extensive experiments on a large-scale driving dataset, nuPlan, with multi-traversal data. Our results demonstrate that MTGS improves LPIPS by 23.5% and geometry accuracy by 46.3% compared to single-traversal baselines. The code and data would be available to the public.
title MTGS: Multi-Traversal Gaussian Splatting
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2503.12552