GS^3: Efficient Relighting with Triple Gaussian Splatting

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bi, Zoubin, Zeng, Yixin, Zeng, Chong, Pei, Fan, Feng, Xiang, Zhou, Kun, Wu, Hongzhi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909350022348800
author Bi, Zoubin
Zeng, Yixin
Zeng, Chong
Pei, Fan
Feng, Xiang
Zhou, Kun
Wu, Hongzhi
author_facet Bi, Zoubin
Zeng, Yixin
Zeng, Chong
Pei, Fan
Feng, Xiang
Zhou, Kun
Wu, Hongzhi
contents We present a spatial and angular Gaussian based representation and a triple splatting process, for real-time, high-quality novel lighting-and-view synthesis from multi-view point-lit input images. To describe complex appearance, we employ a Lambertian plus a mixture of angular Gaussians as an effective reflectance function for each spatial Gaussian. To generate self-shadow, we splat all spatial Gaussians towards the light source to obtain shadow values, which are further refined by a small multi-layer perceptron. To compensate for other effects like global illumination, another network is trained to compute and add a per-spatial-Gaussian RGB tuple. The effectiveness of our representation is demonstrated on 30 samples with a wide variation in geometry (from solid to fluffy) and appearance (from translucent to anisotropic), as well as using different forms of input data, including rendered images of synthetic/reconstructed objects, photographs captured with a handheld camera and a flash, or from a professional lightstage. We achieve a training time of 40-70 minutes and a rendering speed of 90 fps on a single commodity GPU. Our results compare favorably with state-of-the-art techniques in terms of quality/performance. Our code and data are publicly available at https://GSrelight.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11419
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GS^3: Efficient Relighting with Triple Gaussian Splatting
Bi, Zoubin
Zeng, Yixin
Zeng, Chong
Pei, Fan
Feng, Xiang
Zhou, Kun
Wu, Hongzhi
Computer Vision and Pattern Recognition
Graphics
We present a spatial and angular Gaussian based representation and a triple splatting process, for real-time, high-quality novel lighting-and-view synthesis from multi-view point-lit input images. To describe complex appearance, we employ a Lambertian plus a mixture of angular Gaussians as an effective reflectance function for each spatial Gaussian. To generate self-shadow, we splat all spatial Gaussians towards the light source to obtain shadow values, which are further refined by a small multi-layer perceptron. To compensate for other effects like global illumination, another network is trained to compute and add a per-spatial-Gaussian RGB tuple. The effectiveness of our representation is demonstrated on 30 samples with a wide variation in geometry (from solid to fluffy) and appearance (from translucent to anisotropic), as well as using different forms of input data, including rendered images of synthetic/reconstructed objects, photographs captured with a handheld camera and a flash, or from a professional lightstage. We achieve a training time of 40-70 minutes and a rendering speed of 90 fps on a single commodity GPU. Our results compare favorably with state-of-the-art techniques in terms of quality/performance. Our code and data are publicly available at https://GSrelight.github.io/.
title GS^3: Efficient Relighting with Triple Gaussian Splatting
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2410.11419