Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Texture-GS: Disentangling the geometry and texture for 3D gaussian splatting editing

Xu, Tian-Xing, Hu, Wenbo, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Shan, Ying and Zhang, Song-Hai 2024. Texture-GS: Disentangling the geometry and texture for 3D gaussian splatting editing. Presented at: European Conference on Computer Vision (ECCV), Milan, Italy, 29 September - 04 October 2024. Computer Vision – ECCV 2024. , vol.15083 Springer, pp. 37-53. 10.1007/978-3-031-72698-9_3

[thumbnail of TextureGS.pdf]
Preview
PDF - Accepted Post-Print Version
Download (5MB) | Preview

Abstract

3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering. However, it couples the appearance and geometry of the scene within the Gaussian attributes, which hinders the flexibility of editing operations, such as texture swapping. To address this issue, we propose a novel approach, namely Texture-GS, to disentangle the appearance from the geometry by representing it as a 2D texture mapped onto the 3D surface, thereby facilitating appearance editing. Technically, the disentanglement is achieved by our proposed texture mapping module, which consists of a UV mapping MLP to learn the UV coordinates for the 3D Gaussian centers, a local Taylor expansion of the MLP to efficiently approximate the UV coordinates for the ray-Gaussian intersections, and a learnable texture to capture the fine-grained appearance. Extensive experiments on the DTU dataset demonstrate that our method not only facilitates high-fidelity appearance editing but also achieves real-time rendering on consumer-level devices, e.g.a single RTX 2080 Ti GPU.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Publisher: Springer
ISBN: 978-3-031-72697-2
Date of First Compliant Deposit: 18 July 2024
Date of Acceptance: 1 July 2024
Last Modified: 26 Nov 2024 15:50
URI: https://orca.cardiff.ac.uk/id/eprint/170667

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics