Saved in:
Bibliographic Details
Main Authors: Du, Kang, Liang, Zhihao, Shen, Yulin, Wang, Zeyu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.08524
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911089308991488
author Du, Kang
Liang, Zhihao
Shen, Yulin
Wang, Zeyu
author_facet Du, Kang
Liang, Zhihao
Shen, Yulin
Wang, Zeyu
contents Gaussian Splatting (GS) has emerged as an effective representation for photorealistic rendering, but the underlying geometry, material, and lighting remain entangled, hindering scene editing. Existing GS-based methods struggle to disentangle these components under non-Lambertian conditions, especially in the presence of specularities and shadows. We propose \textbf{GS-ID}, an end-to-end framework for illumination decomposition that integrates adaptive light aggregation with diffusion-based material priors. In addition to a learnable environment map for ambient illumination, we model spatially-varying local lighting using anisotropic spherical Gaussian mixtures (SGMs) that are jointly optimized with scene content. To better capture cast shadows, we associate each splat with a learnable unit vector that encodes shadow directions from multiple light sources, further improving material and lighting estimation. By combining SGMs with intrinsic priors from diffusion models, GS-ID significantly reduces ambiguity in light-material-geometry interactions and achieves state-of-the-art performance on inverse rendering and relighting benchmarks. Experiments also demonstrate the effectiveness of GS-ID for downstream applications such as relighting and scene composition.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08524
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors
Du, Kang
Liang, Zhihao
Shen, Yulin
Wang, Zeyu
Computer Vision and Pattern Recognition
Artificial Intelligence
Gaussian Splatting (GS) has emerged as an effective representation for photorealistic rendering, but the underlying geometry, material, and lighting remain entangled, hindering scene editing. Existing GS-based methods struggle to disentangle these components under non-Lambertian conditions, especially in the presence of specularities and shadows. We propose \textbf{GS-ID}, an end-to-end framework for illumination decomposition that integrates adaptive light aggregation with diffusion-based material priors. In addition to a learnable environment map for ambient illumination, we model spatially-varying local lighting using anisotropic spherical Gaussian mixtures (SGMs) that are jointly optimized with scene content. To better capture cast shadows, we associate each splat with a learnable unit vector that encodes shadow directions from multiple light sources, further improving material and lighting estimation. By combining SGMs with intrinsic priors from diffusion models, GS-ID significantly reduces ambiguity in light-material-geometry interactions and achieves state-of-the-art performance on inverse rendering and relighting benchmarks. Experiments also demonstrate the effectiveness of GS-ID for downstream applications such as relighting and scene composition.
title GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.08524