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

DevFeed: [Towards Seconds-level Video Representation: Quadratically Gated Feature Grid with Adaptive, Prediction-free Sampling](<https://devfeed.tech/articles/towards-seconds-level-video-representation-quadratically-gated-feature-grid-with-adaptive-prediction-free-sampling-135113.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17786>)

Author: Tie-Yun Li, Hao-Ran Wang, Chao Wang, Zhiyong Yin, Yiming Xu, Zhenwei Cai, Li Li, Rongzhi Lin, Feng-Lei Fan

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [error](<https://devfeed.tech/tags/error.md>), [faster](<https://devfeed.tech/tags/faster.md>), [grid](<https://devfeed.tech/tags/grid.md>), [hash](<https://devfeed.tech/tags/hash.md>), [model](<https://devfeed.tech/tags/model.md>), [pool](<https://devfeed.tech/tags/pool.md>), [precision](<https://devfeed.tech/tags/precision.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [storage](<https://devfeed.tech/tags/storage.md>), [video](<https://devfeed.tech/tags/video.md>)

## AI overview

Q-GAS combines multi-resolution explicit 3D feature grids, a compact quadratic-gating decoder, and an error-aware sampler to speed up fitting coordinate-queryable video representations. The sampler periodically refreshes a pool of high-error samples from a global error map and mixes them with uniform samples, without an auxiliary predictor. On UVG Beauty, Bosphorus, and Jockey, the authors report fitting and quantization under 50 seconds on one RTX PRO 6000; decoding exceeds 370 FPS with mixed precision and is about 146 FPS in FP32. In their PyTorch implementation, it is 5.5-7.2 times faster than the evaluated Instant-NGP baseline and 19-28 times faster than RNeRV. Under a 90-second budget, it improves PSNR, MS-SSIM, and LPIPS over evaluated NeRV-family pipelines at comparable bit rates across the measured overlap. Explicit grids use modestly more storage, while avoiding hash-collision coefficient sharing.

## Source excerpt

arXiv:2611.17786v1 Announce Type: cross 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 https://github.com/MillenRosen/Q-GAS for readers' free use.