Improving NeRF Quality by Progressive Camera Placement for Unrestricted Navigation in Complex Environments - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Improving NeRF Quality by Progressive Camera Placement for Unrestricted Navigation in Complex Environments

Abstract

Neural Radiance Fields, or NeRFs, have drastically improved novel view synthesis and 3D reconstruction for rendering. NeRFs achieve impressive results on object-centric reconstructions, but the quality of novel view synthesis with free-viewpoint navigation in complex environments (rooms, houses, etc) is often problematic. While algorithmic improvements play an important role in the resulting quality of novel view synthesis, in this work, we show that because optimizing a NeRF is inherently a data-driven process, good quality data play a fundamental role in the final quality of the reconstruction. As a consequence, it is critical to choose the data samples -- in this case the cameras -- in a way that will eventually allow the optimization to converge to a solution that allows free-viewpoint navigation with good quality. Our main contribution is an algorithm that efficiently proposes new camera placements that improve visual quality with minimal assumptions. Our solution can be used with any NeRF model and outperforms baselines and similar work.
Fichier principal
Vignette du fichier
EGauthorGuidelines-Rendering2023-fin_with_teaser.pdf (66.65 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04182002 , version 1 (16-08-2023)

Licence

Identifiers

  • HAL Id : hal-04182002 , version 1

Cite

Georgios Kopanas, George Drettakis. Improving NeRF Quality by Progressive Camera Placement for Unrestricted Navigation in Complex Environments. VMV 2023 - Vision, Modeling, and Visualization, Sep 2023, Braunschweig, Germany. ⟨hal-04182002⟩
70 View
2 Download

Share

Gmail Mastodon Facebook X LinkedIn More