RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery
For satellite 3D reconstruction, this work provides a more accurate rendering method by eliminating approximations inherent in prior Gaussian Splatting approaches.
RPC-GS is the first Gaussian Splatting framework for satellite imagery that natively uses Rational Polynomial Camera (RPC) models, avoiding geometric errors from perspective/affine approximations. It achieves state-of-the-art reconstruction, improving mean altitude error by 29.6% over perspective and 63.8% over affine on DFC2019, and 9.9% and 37.9% on IARPA2016.
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.