Free-GVC: Towards Training-Free Extreme Generative Video Compression with Temporal Coherence

TL;DR

Free-GVC reframes video compression as diffusion-guided latent trajectory coding that operates training-free at the group-of-pictures (GOP) level, leveraging a pretrained video diffusion prior to synthesize temporally coherent reconstructions. It introduces Adaptive Quality Control to online-tune diffusion steps per GOP and Inter-GOP Alignment to fuse overlapping latent regions, significantly reducing flicker across GOP boundaries. Empirically, Free-GVC attains substantial perceptual gains (e.g., a BD-Rate reduction of $93.29\%$ in DISTS vs. DCVC-RT) and is preferred in user studies at ultra-low bitrates, while maintaining competitive distortion metrics. This approach offers a practical path to high-quality generative video compression without model retraining, enabling flexible bitrate control and improved temporal stability in challenging streaming scenarios.

Abstract

Building on recent advances in video generation, generative video compression has emerged as a new paradigm for achieving visually pleasing reconstructions. However, existing methods exhibit limited exploitation of temporal correlations, causing noticeable flicker and degraded temporal coherence at ultra-low bitrates. In this paper, we propose Free-GVC, a training-free generative video compression framework that reformulates video coding as latent trajectory compression guided by a video diffusion prior. Our method operates at the group-of-pictures (GOP) level, encoding video segments into a compact latent space and progressively compressing them along the diffusion trajectory. To ensure perceptually consistent reconstruction across GOPs, we introduce an Adaptive Quality Control module that dynamically constructs an online rate-perception surrogate model to predict the optimal diffusion step for each GOP. In addition, an Inter-GOP Alignment module establishes frame overlap and performs latent fusion between adjacent groups, thereby mitigating flicker and enhancing temporal coherence. Experiments show that Free-GVC achieves an average of 93.29% BD-Rate reduction in DISTS over the latest neural codec DCVC-RT, and a user study further confirms its superior perceptual quality and temporal coherence at ultra-low bitrates.

Figures (11)

• Figure 1: Comparison of generative video compression paradigms. (a) Frame-wise generation introduces frame-level flicker and requires training. (b) Group-wise generation ignores correlations across adjacent groups, leading to temporal discontinuities, and also requires training. (c) Our training-free method fuses inter-group information to achieve temporally coherent compression.
• Figure 2: Qualitative comparison at ultra-low bitrates. The left part illustrates temporal coherence measured by tOF, while the right part compares perceptual quality evaluated by DISTS. Free-GVC achieves the best perceptual quality at the lowest bitrate while maintaining strong temporal consistency. Distortion-oriented codecs, including VVC Bross_2021_TCSVT_VVC, DCVC-RT Jia_25_CVPR_DCVCRT, and DCVC-FM Li_24_CVPR_DCVCFM, preserve temporal coherence but suffer from perceptual degradation. In contrast, generative codecs such as GLC-Video Qi_25_TCSVT_GLCVideo produce rich textures but exhibit misalignment with the ground truth and adjacent frames. $\downarrow$ indicates lower values are better.
• Figure 3: Overview of Free-GVC framework. (a) Inter-GOP Alignment: The input video is divided into GOPs with overlapping frames, which are fused in the latent space during decoding to ensure temporal continuity across GOP boundaries. (b) Diffusion Trajectory Compression: Each latent $\mathbf{y}_k$ is progressively coded along the diffusion trajectory using RCC to obtain $\mathbf{z}_{t^*}$, which is then denoised at the decoder. Gray curves denote possible random denoising paths, with the selected one highlighted in orange and blue. (c) Adaptive Quality Control: An online rate--perception surrogate model predicts the optimal diffusion timestep $t^*$ for each GOP to achieve the target perceptual quality.
• Figure 4: Progressive compression process of frame 24 from the videoSRC25 sequence in the MCL-JCV dataset.
• Figure 5: Fitting performance of different models for the relationship between bitrate and perception across different sequences.