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

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

Read the original on arXiv AI →

The paper introduces Q‑GAS, a coordinate‑queryable video representation that combines multi‑resolution explicit 3D feature grids with a compact SwiGLU‑style quadratic‑gating decoder and an error‑aware, prediction‑free sampler. This design eliminates hash‑collision coefficient sharing, enhances expressive capacity, and improves nonlinear feature response through low‑rank second‑order interactions. Experiments on UVG datasets show that Q‑GAS trains and quantizes 5.5–7.2× faster than Instant‑NGP and 19–28× faster than RNeRV, while achieving higher PSNR, MS‑SSIM, and LPIPS within a 90‑second budget.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computer Vision
Oct 16

ResStreamGS: Residual-Sensitive Dual-Stream Gaussian Splatting for Mobile Volumetric Video Streaming

ResStreamGS introduces a residual‑sensitive dual‑stream framework for mobile volumetric video streaming that distinguishes temporally stable Gaussians from residual‑sensitive ones. Stable Gaussians are transmitted once per Group of Pictures, while only the residual‑sensitive Gaussians are included in the frame‑wise video stream, reducing bandwidth usage. Experiments on complex full‑scene videos show a 7.51–8.35 dB PSNR improvement over a V³‑style baseline, a payload reduction of up to 56.5%, and real‑time performance of 30.883 FPS on a Qualcomm Snapdragon 778G.

By Haoran Liu, Di Wu, Wang Luo, Hengyuan Na, Miao Hu, Guocong Quan
arXiv Machine Learning
Sep 24

ScoutNeRV: Rapid Encoding of Grid-Based Video INRs via ScoutNet

ScoutNeRV introduces a content‑adaptive initialization framework that speeds up the training of hierarchical grid‑based video implicit neural representations (INRs). By using a lightweight scout network to select a pre‑trained expert from a memory bank, the method transfers the expert’s grid and decoder parameters to a target HiNeRV model, achieving a 21.25 dB PSNR boost before fine‑tuning and reaching near‑baseline performance after only 37 epochs. The approach delivers a 9.25× wall‑clock speedup while maintaining competitive rate–distortion performance.

By Naser Alizada, Farhang Baghban, Hashem Pishkar, Ali Mousavi
arXiv Computer Vision
Nov 5

VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation

The paper introduces VAR-Q, a tuning‑free quantization method for KV caches in visual autoregressive models. By grouping cache values along feature and block axes, VAR‑Q eliminates the need for outlier detection or calibration and achieves significant memory savings. Experiments on nine models show up to a 78.5% reduction in KV memory with negligible quality loss, allowing inference batches to grow sixfold.

By Boxun Xu, Jiaji Lu, Yuxuan Yin, Zihu Wang, Ziyue Liu, Yu Wang, Zirui Liu, Peng Li
arXiv Machine Learning
Oct 12

CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches

CORAL-KV is a new framework for compressing the key‑value (KV) cache used by autoregressive video diffusion models. It predicts keys and values across cache layers using block‑diagonal‑plus‑low‑rank (block‑DPLR) predictors, then quantizes only the residuals, offering a flexible trade‑off between fidelity and memory usage. In extensive tests on HY‑WorldPlay and MAGI‑1, the reusable configuration outperforms QVG‑4 by up to 4.95 dB PSNR while reducing cache memory by 37–48 %, and the video‑adapted configuration surpasses QVG‑Pro by 3.77 dB PSNR with 33.7 % less memory, all while maintaining comparable latency and reducing temporal discontinuities.

By Albert Ge, Akash Haridas, Utkarsh Saxena, Ruijing Yang, Ian Colbert, Frederic Sala, Vikram Appia, Emad Barsoum