Guardado en:
Detalles Bibliográficos
Autores principales: Tran, Quan, Dang, Tuan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.06269
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908695508549632
author Tran, Quan
Dang, Tuan
author_facet Tran, Quan
Dang, Tuan
contents 3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render photorealistic images. However, building a 3D Gaussian is guided solely by photometric loss, which can result in inconsistencies in reconstruction. This under-constrained process often results in "floater" artifacts and unstructured geometry, preventing the extraction of high-fidelity surfaces. To address this issue, our paper introduces a novel method that improves reconstruction by enforcing global geometry consistency through constrained multi-view triangulation. Our approach aims to achieve a consensus on 3D representation in the physical world by utilizing various estimated views. We optimize this process by penalizing the deviation of a rendered 3D point from a robust consensus point, which is re-triangulated from a bundle of neighboring views in a self-supervised fashion. We demonstrate the effectiveness of our method across multiple datasets, achieving state-of-the-art results. On the DTU dataset, our method attains a mean Chamfer Distance of 0.50 mm, outperforming comparable explicit methods. We will make our code open-source to facilitate community validation and ensure reproducibility.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06269
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting
Tran, Quan
Dang, Tuan
Computer Vision and Pattern Recognition
3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render photorealistic images. However, building a 3D Gaussian is guided solely by photometric loss, which can result in inconsistencies in reconstruction. This under-constrained process often results in "floater" artifacts and unstructured geometry, preventing the extraction of high-fidelity surfaces. To address this issue, our paper introduces a novel method that improves reconstruction by enforcing global geometry consistency through constrained multi-view triangulation. Our approach aims to achieve a consensus on 3D representation in the physical world by utilizing various estimated views. We optimize this process by penalizing the deviation of a rendered 3D point from a robust consensus point, which is re-triangulated from a bundle of neighboring views in a self-supervised fashion. We demonstrate the effectiveness of our method across multiple datasets, achieving state-of-the-art results. On the DTU dataset, our method attains a mean Chamfer Distance of 0.50 mm, outperforming comparable explicit methods. We will make our code open-source to facilitate community validation and ensure reproducibility.
title TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.06269