cs.CVNov 19, 2026

AGSR: Aperture-Guided Super-Resolution for Gaussian Splatting

Authors: Ayman Alkhateeb, Hadi Amirpour, Christian Timmerer

Organizations: Dept. of Information Technology (ITEC), Alpen-Adria-Universität Klagenfurt, Klagenfurt, Austria

Abstract

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but Gaussian rasterization attenuates fine-scale scene structure through the projected covariance of each primitive. We show that contracting these projected covariances at inference time can mitigate the effective bandwidth limitation induced by finite Gaussian footprints, motivating a multi-aperture rendering framework for super-resolution. Based on this insight, we propose AGSR (Aperture-Guided Super-Resolution), a lightweight inference-time framework that progressively fuses multi-aperture renderings using uncertainty-guided feature aggregation and geometric conditioning from transmittance and depth cues. AGSR operates as a plug-in enhancement for pre-trained 3DGS models. Experiments on the Mip-NeRF 360 benchmark show that AGSR outperforms lightweight image-space super-resolution baselines, with gains increasing as the underlying Gaussian representation deteriorates. The results provide evidence that covariance contraction exposes bandwidth-sensitive structural cues attenuated by native Gaussian rasterization. AGSR achieves these improvements while maintaining real-time performance with up to 139k parameters.

Figures & tables

Explore similar work

CardsList
  1. EffGS: Efficient and High-Fidelity Gaussian Splatting

    Sep 30, 2026Changbai Li, Shuo Yang, Yichen Yang +23D Gaussian Splatting3D Gaussian Pruning

  2. 3DGS3^3: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering

    May 12, 2026Yibo Zhao, Fan Gao, Youcheng Cai +13D Gaussian SplattingVideo Frame Interpolation