arXiv Machine Learning

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.

arXiv Computer Vision
Sep 30

RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution

RelayVSR introduces a streaming video super‑resolution framework that combines a large generative model, which produces reference latents for sparse keyframes, with a lightweight Dual‑Memory Video Transformer that super‑resolves every frame using these references and low‑resolution input. The method employs Video‑Aware Reference Optimization (VARO), a reinforcement‑learning strategy that optimizes both system‑level video quality and reference‑level keyframe fidelity, outperforming direct joint training. On 1080p video, RelayVSR achieves 29.29 FPS with modest GPU memory usage, significantly faster and more efficient than the FlashVSR‑Tiny baseline.

By Xijun Wang, Xin Li, Zirui Lang, Suhang Yao, Haoran Li, Zhibo Chen
arXiv Computer Vision
Sep 7

Scalable Neural Video Representation Compression

Scalable Neural Video Representation Compression (S-NVRC) introduces a scalable implicit neural representation (INR) video codec that supports fine-grained bitrate and decoding‑complexity scalability from a single embedded bitstream. It uses a coarse‑to‑fine prefix for feature grids and a nested prefix for network layers, enabling a wide range of operating points while maintaining a single encoding. On the UVG dataset, S‑NVRC outperforms SHM 12.4 and multi‑layer VTM‑20.0 by 43.7 % and 5.6 % in BD‑rate, respectively, and offers flexible complexity scalability.

By Tianhao Peng, Ho Man Kwan, Fan Zhang, Shan Liu, David Bull
arXiv AI
Sep 4

LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression

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
arXiv Computer Vision
Sep 30

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

TT-VidT is a video pretraining method that decouples the temporal axis by combining a per‑frame ViT-B/16 spatial encoder with a compact Temporal Transfer Layer trained via Diff Compression. The authors conduct a systematic 24‑configuration study to isolate architecture, objective, and decoder effects, showing that the full TT-VidT design yields the strongest motion‑sensitive representations. In downstream fine‑tuning, TT‑VidT outperforms state‑of‑the‑art baselines on Jester, Something‑Something V2, ARID, and Diving48 while using significantly fewer encoder FLOPs.

By Shih-Ying Yeh, Daniel Z. Kaplan, Xuehai Wang, Fu-En Yang, Min-Hung Chen, Shang-Hong Lai
arXiv AI
Aug 28

LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics

LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.

By Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec, Yann LeCun, Randall Balestriero, Florian Buettner
Hugging Face Trending Papers
4d ago

HiVE-VQA: Hierarchical Interaction via Volumetric Embedding for Video Quality Assessment

HiVE-VQA introduces a new approach to no-reference video quality assessment by leveraging a single frozen JEPA-based video foundation model. The method extracts token grids from multiple depths of a pre‑trained V-JEPA 2.1 encoder, stacks them into a hierarchical spatio‑temporal volume, and fuses them with a lightweight 3D convolutional head. With only 5.2 M trainable parameters, HiVE-VQA outperforms 17 state‑of‑the‑art methods on both intra‑dataset and cross‑dataset benchmarks, demonstrating that depth‑wise hierarchical fusion from a frozen backbone is both effective and efficient.

arXiv Computer Vision
Oct 12

Unified Generative Video Compression with Autoregressive and Bidirectional Video Diffusion

The paper introduces UniGVC, a unified generative video codec that supports both low‑delay streaming and high‑quality playback from a single bitstream. It offers two decoding modes: UniGVC‑BI, a bidirectional diffusion model with dense attention for quality‑oriented random‑access decoding, and UniGVC‑AR, a windowed autoregressive diffusion model for low‑delay streaming. Both modes share a hierarchical latent codec that produces ultra‑low‑bitrate conditions, enabling the BI model to act as a teacher for distilling the AR model, while a lightweight conditional decoder further reduces streaming latency.

By Tianyu Zhang, Shuai Huo, Dengchao Jin, Hewei Liu, Meng Lei, Tianwen Wu, Jiawen Gu, Chao Zhou, Li Li, Dong Liu
arXiv AI
1d ago

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

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.

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