Fast Satellite Tensorial Radiance Field for Multi-date Satellite Imagery of Large Size
Tongtong Zhang, Yuanxiang Li

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Advanced Image and Video Retrieval Techniques · Advanced Vision and Imaging
