RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery
Quick Answer
RPC-GS introduces the first Gaussian Splatting framework for satellite imagery using Rational Polynomial Camera (RPC) models, achieving a 29.6% and 63.8% reduction in reconstruction error compared to perspective and affine models on DFC2019.
Quick Take
RPC-GS introduces the first Gaussian Splatting framework for satellite imagery using Rational Polynomial Camera (RPC) models, achieving a 29.6% and 63.8% reduction in reconstruction error compared to perspective and affine models on DFC2019. The framework integrates a robust Jacobian-based covariance projection and a metric ray-based depth formulation, outperforming existing methods on leading satellite benchmark datasets.
Key Points
- RPC-GS uses native RPC models for accurate satellite imagery rendering.
- Achieves 29.6% and 63.8% lower reconstruction errors on DFC2019 compared to other models.
- Integrates a Jacobian-based covariance projection for robust coordinate transformations.
- Introduces a metric ray-based depth formulation to address depth limitations of RPCs.
- Code released to facilitate future research in satellite Gaussian Splatting.
Article Content
From source RSS / original summaryarXiv:2606. 06690v1 Announce Type: new Abstract: We present RPC-GS, the first Gaussian Splatting framework for satellite imagery that operates natively with Rational Polynomial Camera (RPC) models. The RPC model is the de facto standard for representing the complex imaging geometry of modern pushbroom satellite sensors. To simplify rendering, prior satellite Gaussian Splatting methods replace the RPC model with perspective or affine camera approximations, leading to geometric errors during reconstruction.
RPC-GS avoids these approximations by projecting Gaussian means and covariances directly through the RPC model during the splatting process. We embed the RPC model in a chain of carefully selected geo-coordinate transformations representing a mapping from splatting-suitable scene coordinates to image coordinates. To map the Gaussian covariance matrices, we derive a numerically robust Jacobian-based covariance projection for the (partially nonlinear) coordinate transformations.
Since RPCs lack an explicit notion of camera depth, we integrate a metric ray-based depth formulation. We benchmark RPC, perspective, and affine camera models in a unified framework, with our native RPC renderer consistently achieving the lowest reconstruction error on leading satellite benchmark datasets, improving mean altitude error over perspective and affine approximations by 29. 6% and 63. 8% on DFC2019, and by 9. 9% and 37. 9% on IARPA2016.
We release our code to support future research of Gaussian Splatting in the satellite imaging domain.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.
