English

HyperGS: Fast and Generalizable Gaussian Video Representation

Computer Vision and Pattern Recognition 2026-07-13 v1

Abstract

Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow encoding and limits generalization across videos. To amortize this optimization, we propose HyperGS, a feedforward, optimization-free approach that directly predicts Gaussian representations from any video in a single forward pass, speeding up encoding and decoding by orders of magnitude while generalizing to out-of-distribution videos at higher resolutions. In HyperGS, we design a factorized spatiotemporal Transformer to extract tokens from video, and a learnable query-based Transformer to obtain 8-parameter Gaussian representations for each video frame. We find that naively predicting Gaussians across diverse videos induces a needle-like degeneration that collapses training, and address this with a rank-based geometric regularizer whose strength adapts dynamically to stabilize optimization. HyperGS achieves encoding at 10410^4--105×10^5\times the speed of per-video Gaussian optimization at matched reconstruction quality while generalizing zero-shot to 720p720p video, enabling higher-resolution rendering without re-encoding. HyperGS improves PSNR by +2.9--3.1 dB over the prior video encoders on K400, SSv2, and UCF101 at a smaller video representation size. By predicting explicit 2D Gaussians in a single forward pass, HyperGS combines the fast, flexible rendering of Gaussian Splatting with the speed and generalization of feedforward prediction, advancing Gaussians as a practical direction for fast and generalizable video representation.

Cite

@article{arxiv.2607.11500,
  title  = {HyperGS: Fast and Generalizable Gaussian Video Representation},
  author = {Fatimah Zohra and Chen Zhao and Shuming Liu and Yahya Al Malallah and Bernard Ghanem},
  journal= {arXiv preprint arXiv:2607.11500},
  year   = {2026}
}