
CL
Canjie Liu, Liuqian Wang, Qi Ming, Wei Lu, Xiaohan Hao, Yuefei Wu, Wentao Chao, Lei Shi
· 1 min read
ResearcharXiv cs.CV
You Only Encode Once: Sub-Pixel-Shifted Frames for Arbitrary-Scale Remote Sensing Super-Resolution with 2D Gaussian Splatting
arXiv:2611.22898v1 Announce Type: new
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.
Original source
This story was published by arXiv cs.CV and written by Canjie Liu, Liuqian Wang, Qi Ming, Wei Lu, Xiaohan Hao, Yuefei Wu, Wentao Chao, Lei Shi. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


