cs.CVNov 13, 2026

MacroGS: Macro-Pixel Shared Gaussian Primitives for Arbitrary-Scale Light Field Super-Resolutio

Authors: Zeqiang Wei, Angulia Yang, Min Xu

Organizations: Capital Normal University · National University of Singapore

Abstract

Arbitrary-scale light field spatial super-resolution reconstructs high-resolution views at any requested scale from low-resolution multi-view observations. Gaussian primitives enable continuous reconstruction, but generating separate primitive sets for each view redundantly encodes shared scene structure across views and causes the primitive count grow linearly with the number of views. To avoid such redundancy, we propose MacroGS, a feed-forward decoder that jointly predicts a single shared Gaussian set per macro pixel rather than generating separate sets for each view. Disparity-dependent replacement and angle-conditioned appearance allow each set to be reused across all output views, keeping the predicted primitive count independent of the number of views at each requested scale. The decoder iteratively predicts per-primitive disparities, retrieves the corresponding multi-view features, and updates the primitive states. Gaussian splatting and residual refinement then reconstruct the output light field. Despite being learned without geometric supervision, the predicted disparities strongly correlate with underlying scene geometry. Experiments across five benchmarks demonstrate that MacroGS integrates effectively with diverse light field encoders, improving reconstruction quality at fixed scales while achieving leading performance across most evaluated arbitrary-scale settings. The decoder also achieves speedups of approximately 22-10×10\times over state-of-the-art implicit light field decoders and 1010-18×18\times over the view-wise Gaussian baseline.

Figures & tables

Explore similar work

CardsList
  1. Light Field Primitive for Novel View Synthesis

    Sep 25, 2026Liang Chen, Jiahui Ning, Xun Jiang +4Novel View SynthesisNeural Rendering

  2. Sparse Light Field Sampling Improves Casual 3D and 4D Reconstruction

    Aug 20, 2026Shamus Li, Ruiming Cao, Laura Waller +23D ReconstructionSparse-View 4D Reconstruction

  3. PixGR: Pixel-Space Generative Decoding for Fast Feed-Forward 3D Reconstruction

    Oct 22, 2026Ranran Huang, Wenjing Bian, Weixun Luo +2Feed-Forward 3D ReconstructionSparse-View 3D Reconstruction