RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Blanc, Hugo, Deschaud, Jean-Emmanuel, Paljic, Alexis
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916942955151360
author Blanc, Hugo
Deschaud, Jean-Emmanuel
Paljic, Alexis
author_facet Blanc, Hugo
Deschaud, Jean-Emmanuel
Paljic, Alexis
contents RayGauss has achieved state-of-the-art rendering quality for novel-view synthesis on synthetic and indoor scenes by representing radiance and density fields with irregularly distributed elliptical basis functions, rendered via volume ray casting using a Bounding Volume Hierarchy (BVH). However, its computational cost prevents real-time rendering on real-world scenes. Our approach, RayGaussX, builds on RayGauss by introducing key contributions that accelerate both training and inference. Specifically, we incorporate volumetric rendering acceleration strategies such as empty-space skipping and adaptive sampling, enhance ray coherence, and introduce scale regularization to reduce false-positive intersections. Additionally, we propose a new densification criterion that improves density distribution in distant regions, leading to enhanced graphical quality on larger scenes. As a result, RayGaussX achieves 5x to 12x faster training and 50x to 80x higher rendering speeds (FPS) on real-world datasets while improving visual quality by up to +0.56 dB in PSNR. Project page with videos and code: https://raygaussx.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07782
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis
Blanc, Hugo
Deschaud, Jean-Emmanuel
Paljic, Alexis
Computer Vision and Pattern Recognition
RayGauss has achieved state-of-the-art rendering quality for novel-view synthesis on synthetic and indoor scenes by representing radiance and density fields with irregularly distributed elliptical basis functions, rendered via volume ray casting using a Bounding Volume Hierarchy (BVH). However, its computational cost prevents real-time rendering on real-world scenes. Our approach, RayGaussX, builds on RayGauss by introducing key contributions that accelerate both training and inference. Specifically, we incorporate volumetric rendering acceleration strategies such as empty-space skipping and adaptive sampling, enhance ray coherence, and introduce scale regularization to reduce false-positive intersections. Additionally, we propose a new densification criterion that improves density distribution in distant regions, leading to enhanced graphical quality on larger scenes. As a result, RayGaussX achieves 5x to 12x faster training and 50x to 80x higher rendering speeds (FPS) on real-world datasets while improving visual quality by up to +0.56 dB in PSNR. Project page with videos and code: https://raygaussx.github.io/.
title RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.07782