ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitives

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Baranowski, Bartłomiej, Esposito, Stefano, Gschoßmann, Patricia, Chen, Anpei, Geiger, Andreas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914268101738496
author Baranowski, Bartłomiej
Esposito, Stefano
Gschoßmann, Patricia
Chen, Anpei
Geiger, Andreas
author_facet Baranowski, Bartłomiej
Esposito, Stefano
Gschoßmann, Patricia
Chen, Anpei
Geiger, Andreas
contents 3D Gaussian Splatting (3DGS) achieves state-of-the-art image quality and real-time performance in novel view synthesis but often suffers from a suboptimal spatial distribution of primitives. This issue stems from cloning-based densification, which propagates Gaussians along existing geometry, limiting exploration and requiring many primitives to adequately cover the scene. We present ConeGS, an image-space-informed densification framework that is independent of existing scene geometry state. ConeGS first creates a fast Instant Neural Graphics Primitives (iNGP) reconstruction as a geometric proxy to estimate per-pixel depth. During the subsequent 3DGS optimization, it identifies high-error pixels and inserts new Gaussians along the corresponding viewing cones at the predicted depth values, initializing their size according to the cone diameter. A pre-activation opacity penalty rapidly removes redundant Gaussians, while a primitive budgeting strategy controls the total number of primitives, either by a fixed budget or by adapting to scene complexity, ensuring high reconstruction quality. Experiments show that ConeGS consistently enhances reconstruction quality and rendering performance across Gaussian budgets, with especially strong gains under tight primitive constraints where efficient placement is crucial.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06810
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitives
Baranowski, Bartłomiej
Esposito, Stefano
Gschoßmann, Patricia
Chen, Anpei
Geiger, Andreas
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) achieves state-of-the-art image quality and real-time performance in novel view synthesis but often suffers from a suboptimal spatial distribution of primitives. This issue stems from cloning-based densification, which propagates Gaussians along existing geometry, limiting exploration and requiring many primitives to adequately cover the scene. We present ConeGS, an image-space-informed densification framework that is independent of existing scene geometry state. ConeGS first creates a fast Instant Neural Graphics Primitives (iNGP) reconstruction as a geometric proxy to estimate per-pixel depth. During the subsequent 3DGS optimization, it identifies high-error pixels and inserts new Gaussians along the corresponding viewing cones at the predicted depth values, initializing their size according to the cone diameter. A pre-activation opacity penalty rapidly removes redundant Gaussians, while a primitive budgeting strategy controls the total number of primitives, either by a fixed budget or by adapting to scene complexity, ensuring high reconstruction quality. Experiments show that ConeGS consistently enhances reconstruction quality and rendering performance across Gaussian budgets, with especially strong gains under tight primitive constraints where efficient placement is crucial.
title ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitives
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.06810