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:2609.37831v1 Announce Type: new
Abstract: Real-time diffusion-based video super-resolution (VSR) is in high demand for online streaming, yet stringent latency requirements often compromise gene...
By Xijun Wang, Xin Li, Suhang Yao, Zirui Lang, Bingchen Li, Zhibo Chen
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:2610.29691v1 Announce Type: new
Abstract: Generative image compression (GIC) delivers strong perceptual quality at low bitrates. However, GIC methods with strong perceptual quality often rely o...
By Hao Cao, Yinhuan Huang, Wenqi Guo, Zhijin Qin, Jungong Han
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
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
arXiv:2606. 28027v1 Announce Type: cross Abstract: Neural video codecs have surpassed classical codecs in coding efficiency but remain impractical for deployment due to cross-platform incompatibility and high computational cost.
By Tanel P\"arnamaa, Martin Lumiste, Ardi Loot, Evgenii Indenbom, Andrei Znobishchev, Ando Saabas
arXiv:2607. 14898v1 Announce Type: cross Abstract: Real-time video generation demands fast decoding as much as fast denoising, yet current latent video diffusion models rely on 3D convolutional decoders that are slow and memory-intensive at high resolutions or for long video.
By Minguk Kang, Suha Kwak
arXiv:2608. 19639v1 Announce Type: new Abstract: Streaming reconstruction of Free-Viewpoint Videos (FVVs) supports immersive Internet of Things (IoT) services, such as telepresence and digital twin visualization.
By Yiwei Li, Jiannong Cao, Weixun Gao, Rui Cao, Songye Zhu, Yinfeng Cao, Mingjin Zhang
arXiv:2610.27712v1 Announce Type: cross
Abstract: Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that m...
By Injae Kim, Minseok Joo, Jihwan Park, Sehyung Kim, Minseong Bae, Hyunwoo J. Kim
FastBench is a new benchmark that tests streaming Video‑Large‑Language Models (VLMs) on high‑dynamic real‑world video streams, where events occur rapidly and cannot be captured by sparse 1–2 FPS sampling. The benchmark uses a trajectory‑grounded pipeline that generates QA pairs from high‑FPS clips, filters questions answerable at 2 FPS, verifies answers with SAM3 and CoTracker3 trajectories, and incorporates three rounds of human inspection, yielding 306 QA pairs across eight domains and multiple temporal scopes. Experiments show that even the strongest model, Gemini‑3.5‑Flash, achieves only 50.7 % accuracy, and that denser sampling improves performance but saturates when history is compressed; a training‑free baseline, ProactiveFrame, outperforms uniform sampling but still falls short of oracle‑guided focusing.
By Yuxuan Hu, Weikang Shi, Yang Bo, Xudong Lu, Xintong Guo, Shuhan Li, Yuyang He, Huankang Guan, Peiwen Sun, Yunqiao Yang, Wenbo Li, Rui Liu, Hongsheng Li
LRConv-NeRV introduces low‑rank separable convolutions into the NeRV neural video decoder, replacing selected dense 3x3 layers to reduce computational load and memory usage. By applying low‑rank factorization progressively from the largest to earlier decoder stages, the method offers controllable trade‑offs between reconstruction quality and efficiency. Experiments show that applying LRConv only to the final decoder stage cuts decoder complexity by 68% and model size by 9.3% with negligible quality loss, while INT8 quantization preserves performance close to the dense baseline.
By Tamer Shanableh