# GVC-RT: Towards Real-Time Generative Video Compression at Ultra-Low Bitrates

arXiv: https://arxiv.org/abs/2608.04891 · HTML: https://mlsanity.com/paper/2608.04891/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation](https://mlsanity.com/paper/2409.04410/) (2024)
- [FVC: A New Framework towards Deep Video Compression in Feature Space](https://mlsanity.com/paper/2105.09600/) (2021)
- [Neural Video Compression with Feature Modulation](https://mlsanity.com/paper/2402.17414/) (2024)
- [Towards Practical Real-Time Neural Video Compression](https://mlsanity.com/paper/2502.20762/) (2025)
- [FloLPIPS: A Bespoke Video Quality Metric for Frame Interpoation](https://mlsanity.com/paper/2207.08119/) (2022)
- [Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse](https://mlsanity.com/paper/2501.13528/) (2025)
- [Generative Neural Video Compression via Video Diffusion Prior](https://mlsanity.com/paper/2512.05016/) (2025)
- [Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance](https://mlsanity.com/paper/2512.07480/) (2025)
- [DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework](https://mlsanity.com/paper/2508.07682/) (2025)
- [YODA: Yet Another One-step Diffusion-based Video Compressor](https://mlsanity.com/paper/2601.01141/) (2026)
- [Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder](https://mlsanity.com/paper/2512.12229/) (2025)
- [DiffVC-RT: Towards Practical Real-Time Diffusion-based Perceptual Neural Video Compression](https://mlsanity.com/paper/2601.20564/) (2026)

## Built on by (most cited first, 1 of 1)

- [A Spatiotemporal Semantic Importance-Guided Unified Compression and Editing Framework for AI-Generated Videos](https://mlsanity.com/paper/2610.05779/) (2026)

## Abstract (arXiv)

Recent generative video codecs (GVCs) have achieved impressive reconstruction fidelity at ultra-low bitrates (< 0.02 bits per pixel) by compressing the tokens from generative tokenizers. However, existing GVCs generally require considerable computation time and model complexity, which hinder their deployment on compute-limited devices and in real-time applications. To bridge this gap, we systematically identify the computational bottlenecks and propose GVC-RT, which redesigns the generative latent coding framework to realize real-time video coding without sacrificing compression performance. Specifically, built on a pretrained lookup-free quantization (LFQ) tokenizer, GVC-RT adopts an asymmetric architecture that directly learns to match the LFQ latent distribution, while generative-space alignment is enforced via a regularization loss term only during training. In this manner, we bypass heavy tokenization and entirely remove the complex feature-alignment process at inference time. Moreover, we further introduce a lightweight de-tokenizer architecture to resolve the final latency bottleneck during decoding. Experimental results demonstrate that GVC-RT outperforms the previous SOTA model, GLC-Video, with average BD-rate savings of 12.4% and 48.8% in terms of DISTS and LPIPS, while achieving encoding/decoding speeds of 123.1/55.1 fps for 1080p video. The code is at https://github.com/semcomm/GVC-RT.