3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Taktasheva, Maria, Goli, Lily, Fiorini, Alessandro, Li, Zhen, Rebain, Daniel, Tagliasacchi, Andrea
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916963245096960
author Taktasheva, Maria
Goli, Lily
Fiorini, Alessandro
Li, Zhen
Rebain, Daniel
Tagliasacchi, Andrea
author_facet Taktasheva, Maria
Goli, Lily
Fiorini, Alessandro
Li, Zhen
Rebain, Daniel
Tagliasacchi, Andrea
contents Recent advances in radiance fields and novel view synthesis enable creation of realistic digital twins from photographs. However, current methods struggle with flat, texture-less surfaces, creating uneven and semi-transparent reconstructions, due to an ill-conditioned photometric reconstruction objective. Surface reconstruction methods solve this issue but sacrifice visual quality. We propose a novel hybrid 2D/3D representation that jointly optimizes constrained planar (2D) Gaussians for modeling flat surfaces and freeform (3D) Gaussians for the rest of the scene. Our end-to-end approach dynamically detects and refines planar regions, improving both visual fidelity and geometric accuracy. It achieves state-of-the-art depth estimation on ScanNet++ and ScanNetv2, and excels at mesh extraction without overfitting to a specific camera model, showing its effectiveness in producing high-quality reconstruction of indoor scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16423
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
Taktasheva, Maria
Goli, Lily
Fiorini, Alessandro
Li, Zhen
Rebain, Daniel
Tagliasacchi, Andrea
Computer Vision and Pattern Recognition
Recent advances in radiance fields and novel view synthesis enable creation of realistic digital twins from photographs. However, current methods struggle with flat, texture-less surfaces, creating uneven and semi-transparent reconstructions, due to an ill-conditioned photometric reconstruction objective. Surface reconstruction methods solve this issue but sacrifice visual quality. We propose a novel hybrid 2D/3D representation that jointly optimizes constrained planar (2D) Gaussians for modeling flat surfaces and freeform (3D) Gaussians for the rest of the scene. Our end-to-end approach dynamically detects and refines planar regions, improving both visual fidelity and geometric accuracy. It achieves state-of-the-art depth estimation on ScanNet++ and ScanNetv2, and excels at mesh extraction without overfitting to a specific camera model, showing its effectiveness in producing high-quality reconstruction of indoor scenes.
title 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.16423