You Only Encode Once: Sub-Pixel-Shifted Frames for Arbitrary-Scale Remote Sensing Super-Resolution with 2D Gaussian Splatting

Canjie Liu, Liuqian Wang, Qi Ming, Wei Lu, Xiaohan Hao, Yuefei Wu, Wentao Chao, Lei ShiarXiv 2026 · arXiv

TL;DR

SPS-GS (Sub-Pixel-Shifted Gaussian Splatting) is a new framework for arbitrary-scale remote sensing super-resolution that achieves multi-frame performance with the efficiency of a single-pass encoder. By synthesizing sub-pixel shifted frames during training and employing 2D Gaussian Splatting for continuous rendering, it effectively recovers high-frequency details from aliased signals while remaining significantly faster than traditional implicit neural representation (INR) methods.

What Problem Does This Paper Address?

Remote sensing imagery is often constrained by sensor resolution, yet downstream applications—like environmental monitoring or geographic analysis—frequently require images at various spatial scales. This is the domain of Arbitrary-Scale Super-Resolution (ASSR).

Current approaches fall into two camps, both with significant drawbacks:

  1. Single-Image ASSR: These methods use a single low-resolution (LR) observation. Because LR sampling discards high-frequency information, the problem is underconstrained, and the results often lack fine detail.
  2. Multi-Frame SR: These methods use multiple observations of the same scene to exploit complementary sub-pixel information. However, they typically require repeated feature encoding for every frame and specialized multi-frame training sequences, leading to high computational costs and data acquisition hurdles.

Furthermore, most multi-frame methods treat aliasing (the jagged artifacts caused by under-sampling) as noise to be suppressed. The authors of this paper argue that aliasing actually contains valuable high-frequency information if you can correctly demodulate the phase shifts between frames.

Methods

The authors propose SPS-GS, an "encode-once" framework that integrates multi-frame information before the deep encoding pass.

Figure 1. Motivation and comparison of three SR paradigms. (a) Single-image ASSR is limited by the sampling information available from one LR observation. (b) Conventional multi-frame SR exploits complementary observations but often involves re- peated feature encoding and spatial-domain alignment, which may suppress aliasing information. (c) SPS-GS synthesizes comple- mentary LR frames from a single HR image during training and performs phase-aware fusion before a single deep encoding pass at inference.

The architecture consists of three main components:

  • Sub-Pixel-Shifted Training: To avoid the need for real-world multi-frame training sets, the model synthesizes $K$ sub-pixel-shifted LR frames from a single high-resolution (HR) image during training. This allows the model to learn multi-frame fusion using standard single-image datasets.
  • Phase-Coherent Aliasing Demodulation (PCAD): This module aligns non-reference frames to a reference grid using Fourier-domain phase modulation. It then uses a phase-aware branch and regularized least-squares estimation to extract and fuse the complementary aliasing information. Crucially, this happens before the main encoder, allowing the network to "encode once."
  • Gaussian Projection Alignment (GPA): Instead of using standard pixels or MLPs, the model represents the image as a set of 2D Gaussians. GPA iteratively refines the centers and colors of these Gaussians by back-projecting reconstruction errors from all $K$ observations. This ensures the final HR output is consistent with all input LR frames.
Figure 2. Overview of SPS-GS. During training, multiple sub-pixel-shifted LR frames are synthesized from a single HR image (left). PCAD (middle) integrates complementary aliasing information through Fourier alignment, phase-aware fusion, and regularized least- squares estimation before a single deep encoding pass. GPA (right) iteratively refines Gaussian colors and centers through multi-frame back-projection, enabling arbitrary-scale rendering. At inference, the framework directly takes multiple LR observations as input.

Datasets

The model was evaluated on five standard remote sensing benchmarks: AID, UCMerced, WHU-RS19, RSSCN7, and NWPU-RESISC45.

To test real-world performance, the authors also evaluated the model on three multi-frame datasets:

  • PROBA-V: Satellite imagery at $\times 3$ scale.
  • WorldStrat: Multi-temporal satellite imagery at $\times 4$ scale.
  • RealBSR-RGB: A burst super-resolution dataset.

Key Insights and Ideas

  • Aliasing as a Signal, Not Noise: By recognizing that sub-pixel shifts introduce distinct phase modulations to aliased components, the authors turned a sampling artifact into a source of high-frequency data.
  • Efficiency through Splatting: Traditional ASSR methods use Implicit Neural Representations (INRs), which require querying a heavy MLP for every single pixel in the output image. By using 2D Gaussian Splatting, the model can render high-resolution images much faster, as splatting is a highly efficient rasterization process.
  • Synthetic-to-Real Transfer: The paper demonstrates that a model trained entirely on synthetic sub-pixel shifts can generalize effectively to real-world multi-frame satellite data, significantly lowering the barrier for training multi-frame SR models.

Key Results

SPS-GS consistently outperformed both single-image and multi-frame baselines across all datasets and scales.

  • Accuracy: On the AID dataset at $\times 4$ scale, SPS-GS achieved a PSNR of 32.72 dB, outperforming the best multi-frame baseline (ST-AVSR) by 0.45 dB and single-image methods by over 3 dB.
  • Generalization: The model showed strong performance at "unseen" scales (e.g., $\times 8$ and $\times 16$) that were not encountered during training.
  • Speed: Due to the "encode-once" design and Gaussian rendering, SPS-GS is roughly 7x to 10x faster than INR-based decoders like LIIF or LTE at common scales.
Figure 3. Qualitative comparison on AID at ×8 (unseen scale). Red boxes show zoomed regions; PSNR is measured on full images. Selected high-gain examples are shown here, with random examples in the Appendix.

Limitations and Future Work

While SPS-GS is a significant step forward, the authors note a few areas for improvement:

  • Radiometric Consistency: The current model assumes frames have consistent brightness and contrast. Real satellite imagery often suffers from radiometric variations between passes.
  • Environmental Factors: The framework does not yet explicitly handle cloud interference or significant parallax (3D) effects caused by different viewing angles in satellite bursts.
  • Refinement Iterations: While GPA improves accuracy, the iterative nature of the refinement adds some computational overhead, though it remains faster than many competitors.
Figure 4. Analysis of reconstruction gains. (a) Effect of frame count. (b) Effect of GPA iterations. (c) PSNR gains versus texture complexity. (d) Relative deviations from Fourier-based alignment (reference: 0%).

Summary updated

Abstract

Arbitrary-scale super-resolution (ASSR) of remote sensing images remains challenging due to the limited high-frequency information in a single low-resolution (LR) observation. While multi-frame SR can exploit complementary sub-pixel information, existing approaches often require real multi-frame training sequences and repeated feature encoding, increasing data acquisition demands and computational costs. To address these limitations, we propose SPS-GS (Sub-Pixel-Shifted Gaussian Splatting), an encode-once framework that learns from multi-phase LR observations synthesized from individual high-resolution images, without requiring real multi-frame training sequences. Specifically, Phase-Coherent Aliasing Demodulation (PCAD) exploits shift-dependent aliasing through Fourier-based alignment, phase-aware residual fusion, and least-squares aliasing estimation, enabling multi-frame information to be integrated before a single deep encoding pass. Gaussian Projection Alignment (GPA) then iteratively refines Gaussian centers and colors using multi-observation back-projection to promote observation consistency. The refined Gaussians support continuous rendering at arbitrary scales. Extensive experiments on five remote sensing datasets demonstrate strong reconstruction performance against single-image and multi-frame SR baselines, while maintaining competitive inference efficiency at common scales. The code will be publicly released.
BibTeX
@misc{liu2026you,
  author = {Canjie Liu and Liuqian Wang and Qi Ming and Wei Lu and Xiaohan Hao and Yuefei Wu and Wentao Chao and Lei Shi},
  title = {{You Only Encode Once: Sub-Pixel-Shifted Frames for Arbitrary-Scale Remote Sensing Super-Resolution with 2D Gaussian Splatting}},
  year = {2026},
  eprint = {2611.22898},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.22898},
}
Figure