Fast Satellite Tensorial Radiance Field for Multi-date Satellite Imagery of Large Size

TL;DR

SatensoRF is a fast, parameter-efficient neural radiance field model tailored for large-scale multi-date satellite imagery, addressing speed, size, and surface reflectance limitations of prior models.

Contribution

The paper introduces SatensoRF, a multiscale tensor decomposition approach that accelerates satellite image rendering, handles large images efficiently, and models specular surfaces without requiring solar information.

Findings

Outperforms state-of-the-art Sat-NeRF in view synthesis

Requires fewer parameters, enabling faster training and inference

Effectively models specular surfaces and multi-date inconsistencies

Abstract

Existing NeRF models for satellite images suffer from slow speeds, mandatory solar information as input, and limitations in handling large satellite images. In response, we present SatensoRF, which significantly accelerates the entire process while employing fewer parameters for satellite imagery of large size. Besides, we observed that the prevalent assumption of Lambertian surfaces in neural radiance fields falls short for vegetative and aquatic elements. In contrast to the traditional hierarchical MLP-based scene representation, we have chosen a multiscale tensor decomposition approach for color, volume density, and auxiliary variables to model the lightfield with specular color. Additionally, to rectify inconsistencies in multi-date imagery, we incorporate total variation loss to restore the density tensor field and treat the problem as a denosing task.To validate our approach, we conducted assessments of SatensoRF using subsets from the spacenet multi-view dataset, which includes both multi-date and single-date multi-view RGB images. Our results clearly demonstrate that SatensoRF surpasses the state-of-the-art Sat-NeRF series in terms of novel view synthesis performance. Significantly, SatensoRF requires fewer parameters for training, resulting in faster training and inference speeds and reduced computational demands.