Splat and Replace: 3D Reconstruction with Repetitive Elements
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915331872653312 |
|---|---|
| author | Violante, Nicolás Meuleman, Andreas Gauthier, Alban Durand, Frédo Groueix, Thibault Drettakis, George |
| author_facet | Violante, Nicolás Meuleman, Andreas Gauthier, Alban Durand, Frédo Groueix, Thibault Drettakis, George |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06462 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Splat and Replace: 3D Reconstruction with Repetitive Elements Violante, Nicolás Meuleman, Andreas Gauthier, Alban Durand, Frédo Groueix, Thibault Drettakis, George Graphics Computer Vision and Pattern Recognition 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. |
| title | Splat and Replace: 3D Reconstruction with Repetitive Elements |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.06462 |