# GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression

arXiv: https://arxiv.org/abs/2608.03517 · HTML: https://mlsanity.com/paper/2608.03517/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 42 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 28 of 28)

- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [Lossy Compression with Gaussian Diffusion](https://mlsanity.com/paper/2206.08889/) (2022)
- [Towards Practical Real-Time Neural Video Compression](https://mlsanity.com/paper/2502.20762/) (2025)
- [DiCache: Let Diffusion Model Determine Its Own Cache](https://mlsanity.com/paper/2508.17356/) (2025)
- [MagCache: Fast Video Generation with Magnitude-Aware Cache](https://mlsanity.com/paper/2506.09045/) (2025)
- [Compressed Image Generation with Denoising Diffusion Codebook Models](https://mlsanity.com/paper/2502.01189/) (2025)
- [Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression](https://mlsanity.com/paper/2505.16177/) (2025)
- [Generative Neural Video Compression via Video Diffusion Prior](https://mlsanity.com/paper/2512.05016/) (2025)
- [Free-GVC: Towards Training-Free Extreme Generative Video Compression with Temporal Coherence](https://mlsanity.com/paper/2602.09868/) (2026)
- [Generative Latent Video Compression](https://mlsanity.com/paper/2510.09987/) (2025)
- [M3-CVC: Controllable Video Compression with Multimodal Generative Models](https://mlsanity.com/paper/2411.15798/) (2024)
- [T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates](https://mlsanity.com/paper/2507.07633/) (2025)
- [TaoCache: Structure-Maintained Video Generation Acceleration](https://mlsanity.com/paper/2508.08978/) (2025)
- [PSC: Posterior Sampling-Based Compression](https://mlsanity.com/paper/2407.09896/) (2024)
- [Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression](https://mlsanity.com/paper/2511.06424/) (2025)
- [Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache](https://mlsanity.com/paper/2602.22654/) (2026)
- [GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow](https://mlsanity.com/paper/2603.26571/) (2026)
- [Low-Bitrate Video Compression through Semantic-Conditioned Diffusion](https://mlsanity.com/paper/2512.00408/) (2025)
- [Generative Video Compression with One-Dimensional Latent Representation](https://mlsanity.com/paper/2603.15302/) (2026)
- [Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models](https://mlsanity.com/paper/2510.23633/) (2025)
- [ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling](https://mlsanity.com/paper/2603.17546/) (2026)
- [Advances in Diffusion-Based Generative Compression](https://mlsanity.com/paper/2601.18932/) (2026)
- [Dense-Prior-Guided Generative Video Compression](https://mlsanity.com/paper/2604.06655/) (2026)

## Abstract (arXiv)

Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to guide reconstruction at ultra-low bitrate. Current codecs tie each finite-rate correction to a fresh prior evaluation, so shortening the sampler also removes correction slots that carry target-dependent information. We propose GVCCTurbo, a BPP-driven scheduler that separates expensive prior refreshes from codebook corrections: after calibrating an atom-count operating point and skip-gap ratio once per protocol, it maps a target codebook-payload bitrate to a trajectory length and refresh period, making BPP a schedule input instead of a fixed consequence of sampler length. The same endpoint-prediction and finite-rate steering interface covers GVCC-style rectified-flow video and DDCM-style diffusion image compression, preserving zero-training deployment and compatibility with future distilled priors. Native 1080p curves position the complete zero-shot codec in the ultra-low-bitrate regime. In a controlled 720p Wan-GVCC study, the scheduler cuts prior evaluations from 20 to 9 for a ~!44% measured decoding-time reduction shared across the whole schedule family, at a small shared LPIPS cost on high-motion content; within that family, uniform refresh thinning (pure-skip) is a boundary point, and the BPP-aware interior point trades 2.9% fewer codebook-payload bits for consistently higher PSNR at comparable LPIPS. These results support BPP-to-compute scheduling as a controllable extension of sampler-length tuning, without requiring the allocated point to dominate every boundary point.