AI summaryⓘ
The authors developed a new method called BRF-GS to better capture how surfaces reflect light from different angles, especially for complex scenes with detailed color information found in hyperspectral images. They improved an existing 3D representation technique by adding a special part that models directional light reflection more accurately. Their approach also carefully picks reliable color data to build the 3D scene and trains the model in two steps to separate shape and color learning. They created a new dataset to test their method and showed it works well for producing realistic images from multiple viewpoints. This work helps improve how remote sensing systems simulate and understand surface reflections.
Bidirectional Reflectance Factor (BRF)3D Gaussian Splatting (3DGS)Hyperspectral ImagingRadiative TransferBidirectional Reflectance Distribution Function (BRDF)Neural Scene RepresentationMulti-angle ImagerySpectral BandsRemote Sensing
Authors
Yiling Yao, Wenjuan Zhang, Bowen Wang, Bocheng Li, Wentao Song, Bing Zhang
Abstract
The bidirectional reflectance factor (BRF) characterizes the directional radiative properties of terrestrial surfaces. However, existing three-dimensional (3D) radiative transfer models require complex scene construction and computationally intensive radiative transfer solvers, limiting efficient generation of multi-angle hyperspectral reflectance imagery. 3D Gaussian Splatting (3DGS) offers an efficient framework for neural scene representation and novel view synthesis, but its low-order spherical harmonics representation is insufficient for complex directional reflectance, while the high dimensionality and inter-band quality differences of hyperspectral data introduce additional challenges. To address these challenges, we propose BRF-GS, a 3DGS-based framework for BRF modeling and hyperspectral reflectance image generation. BRF-GS introduces a hybrid BRDF-driven kernel to represent complex directional reflectance, selects geometry-reliable spectral bands for robust 3D scene initialization, and adopts a two-stage training strategy that decouples geometry optimization from spectral modeling. We further construct the AIR-BRF dataset, a multi-angle hyperspectral directional reflectance dataset comprising three scenes with diverse natural and artificial targets. Experiments demonstrate that BRF-GS achieves superior spatial and spectral fidelity and accurately reproduces characteristic view-dependent BRF responses. The proposed framework provides an efficient data-driven approach for BRF modeling and multi-angle hyperspectral reflectance image generation in remote sensing scenes.