arXiv AI By Yingwen Zhang, Meng Wang, Liqiang He, Shiqi Wang

Can LLMs Design Video Coding Tools? A Case Study on Planar Mode

Read the original on arXiv AI →

The paper investigates whether large language models (LLMs) can design video coding tools, focusing on the Planar mode used in video coding standards. Using a generation-and-evaluation loop, the LLM generates new Planar predictors, which are then tested in the Fraunhofer Versatile Video Encoder (VVenC) and the Enhanced Compression Model (ECM). Results show that the LLM-generated mode can outperform the conventional Planar mode, achieving a 0.18% bitrate saving with a 0.4% complexity increase, and that similar gains are possible when integrating the new predictor into ECM under low‑resolution settings.

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
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 Computer Vision
Sep 7

Multi-scale Image Representation Compression

The paper introduces MIRC, an overfitted image codec that quantizes and entropy‑codes all components—including latents, synthesis network, and entropy models—within a single end‑to‑end rate‑distortion framework inspired by NVRC. It adds a multi‑scale representation with cross‑stage parameter sharing to capture cross‑scale redundancy, yielding a 10.5 % BD‑rate saving over VVC on the CLIC2020 professional set. MIRC offers multiple configurations ranging from 1.2 to 2.9 kMAC per pixel, allowing decoding complexity to be tuned to deployment needs.

By Tianhao Peng, Ho Man Kwan, Fan Zhang, Shan Liu, David Bull
arXiv Computer Vision
Aug 31

Visual Token Coding for Video Multimodal Large Language Models

The paper introduces Visual Token Coding (VTC), a token compression method for video multimodal large language models that mimics classical video coding by predicting I/P frames and measuring residuals to reduce token redundancy. VTC is extended with dynamic features—Dynamic Resolution Input, Dynamic Token Allocation, and Spatial Coverage Top‑K—forming VTC_Dy, which can be applied to existing MLLMs without additional tuning. Experiments on three MLLMs and multiple video benchmarks show that VTC_Dy retains over 100% of average performance with a 50% token budget and 97.8% with a 25% budget, while the code is publicly available.

By Chenxin Fang, Tao Chen, JunChao You, Jun Peng, Yiyi Zhou, Rongrong Ji