Splat and Replace: 3D Reconstruction with Repetitive Elements
Name
3721238.3730727.pdf
Size
77.95 MB
Format
Adobe PDF
Checksum (MD5)
b2128b25478a7b80a6b17c0b8026c526
Author(s)
Violante, Nicolas
Meuleman, Andr?as
Gauthier, Alban
Durand, Fredo
Groueix, Thibault
Drettakis, George
Date Issued
July 27, 2025
Publisher
ACM|Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers
Citation
Nicolas Violante, Andréas Meuleman, Alban Gauthier, Fredo Durand, Thibault Groueix, and George Drettakis. 2025. Splat and Replace: 3D Reconstruction with Repetitive Elements. In Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers (SIGGRAPH Conference Papers '25). Association for Computing Machinery, New York, NY, USA, Article 20, 1–12.
Version
Final published version
Abstract
We leverage repetitive elements in 3D scenes to improve novel view synthesis. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have greatly improved novel view synthesis but renderings of unseen and occluded parts remain low-quality if the training views are not exhaustive enough. Our key observation is that our environment is often full of repetitive elements. We propose to leverage those repetitions to improve the reconstruction of low-quality parts of the scene due to poor coverage and occlusions. We propose a method that segments each repeated instance in a 3DGS reconstruction, registers them together, and allows information to be shared among instances. Our method improves the geometry while also accounting for appearance variations across instances. We demonstrate our method on a variety of synthetic and real scenes with typical repetitive elements, leading to a substantial improvement in the quality of novel view synthesis.
Description
SIGGRAPH Conference Papers ’25, Vancouver, BC, Canada
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3721238.3730727
