Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wilczyński, Grzegorz, Zieliński, Mikołaj, Byrski, Krzysztof, Waczyńska, Joanna, Belter, Dominik, Spurek, Przemysław
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.15368
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914398310760448
author Wilczyński, Grzegorz
Zieliński, Mikołaj
Byrski, Krzysztof
Waczyńska, Joanna
Belter, Dominik
Spurek, Przemysław
author_facet Wilczyński, Grzegorz
Zieliński, Mikołaj
Byrski, Krzysztof
Waczyńska, Joanna
Belter, Dominik
Spurek, Przemysław
contents Neural Radiance Fields achieve high-fidelity scene representation but suffer from costly training and rendering, while 3D Gaussian splatting offers real-time performance with strong empirical results. Recently, solutions that harness the best of both worlds by using Gaussians as proxies to guide neural field evaluations, still suffer from significant computational inefficiencies. They typically rely on stochastic volumetric sampling to aggregate features, which severely limits rendering performance. To address this issue, a novel framework named IRIS (Intersection-aware Ray-based Implicit Editable Scenes) is introduced as a method designed for efficient and interactive scene editing. To overcome the limitations of standard ray marching, an analytical sampling strategy is employed that precisely identifies interaction points between rays and scene primitives, effectively eliminating empty space processing. Furthermore, to address the computational bottleneck of spatial neighbor lookups, a continuous feature aggregation mechanism is introduced that operates directly along the ray. By interpolating latent attributes from sorted intersections, costly 3D searches are bypassed, ensuring geometric consistency, enabling high-fidelity, real-time rendering, and flexible shape editing. Code can be found at https://github.com/gwilczynski95/iris.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15368
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle IRIS: Intersection-aware Ray-based Implicit Editable Scenes
Wilczyński, Grzegorz
Zieliński, Mikołaj
Byrski, Krzysztof
Waczyńska, Joanna
Belter, Dominik
Spurek, Przemysław
Computer Vision and Pattern Recognition
Neural Radiance Fields achieve high-fidelity scene representation but suffer from costly training and rendering, while 3D Gaussian splatting offers real-time performance with strong empirical results. Recently, solutions that harness the best of both worlds by using Gaussians as proxies to guide neural field evaluations, still suffer from significant computational inefficiencies. They typically rely on stochastic volumetric sampling to aggregate features, which severely limits rendering performance. To address this issue, a novel framework named IRIS (Intersection-aware Ray-based Implicit Editable Scenes) is introduced as a method designed for efficient and interactive scene editing. To overcome the limitations of standard ray marching, an analytical sampling strategy is employed that precisely identifies interaction points between rays and scene primitives, effectively eliminating empty space processing. Furthermore, to address the computational bottleneck of spatial neighbor lookups, a continuous feature aggregation mechanism is introduced that operates directly along the ray. By interpolating latent attributes from sorted intersections, costly 3D searches are bypassed, ensuring geometric consistency, enabling high-fidelity, real-time rendering, and flexible shape editing. Code can be found at https://github.com/gwilczynski95/iris.
title IRIS: Intersection-aware Ray-based Implicit Editable Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.15368