跳到正文
arXiv cs.AI· Tie-Yun Li, Hao-Ran Wang, Chao Wang, Zhiyong Yin, Yiming Xu, Zhenwei Cai, Li Li, Rongzhi Lin, Feng-Lei Fan·· 4 小时前AI 评分34

Q-GAS:面向秒级视频表示的二次门控特征网格与自适应免预测采样方法

Towards Seconds-level Video Representation: Quadratically Gated Feature Grid with Adaptive, Prediction-free Sampling

AI 导读

研究者提出坐标可查询的视频表示 Q-GAS,结合多分辨率显式 3D 特征网格、SwiGLU 风格二次门控(QG)解码器和误差感知的免预测采样器。

正文 · 原文

View PDF HTML (experimental)

Abstract:Implicit neural video representations are notoriously slow to build, which does not cross the basic practical threshold for most industrial applications. Here, we present Q-GAS, a coordinate-queryable video representation that couples multi-resolution explicit 3D feature grids with a compact SwiGLU-style quadratic-gating (QG) decoder and an error-aware, prediction-free sampler. The explicit grids avoid hash-collision coefficient sharing at the cost of modestly higher storage yet greatly boost the expressive capacity; the QG decoder introduces low-rank local second-order interactions to improve the nonlinear feature response. During fitting, a global error map periodically refreshes a high-error pool, and each batch mixes pool samples with uniform samples, which is free from the auxiliary model to predict difficult samples, thereby further escalating the efficiency. On UVG Beauty/Bosphorus/Jockey, Q-GAS fits and quantizes under 50 s on one RTX PRO 6000, decodes at over 370 FPS with mixed precision and about 146 FPS in FP32. In our PyTorch implementation, Q-GAS trains and quantizes 5.5-7.2 times faster than the evaluated Instant-NGP baseline and 19-28 times faster than RNeRV. Under a 90 s budget, it improves PSNR/MS-SSIM/LPIPS over the evaluated NeRV-family pipelines at comparable BPP over the measured overlap. We have shared our code at this https URL for readers' free use.
Comments: 13 pages, 11 figures, 4 tables. Code available at this https URL
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.17786 [cs.CV]
  (or arXiv:2611.17786v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.17786

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Tieyun Li [view email]
[v1] Fri, 13 Nov 2026 06:00:40 UTC (23,168 KB)

来源:arXiv cs.AI · arxiv.org