{"slug": "diffvc-one-diffusion-based-generative-video-compression-with-one-step-video", "title": "DiffVC-ONE: Diffusion-based Generative Video Compression with One-Step Video Diffusion Transformer", "summary": "Researchers propose DiffVC-ONE, a diffusion-based generative video compression framework built on a one-step Video Diffusion Transformer, achieving state-of-the-art perceptual quality and temporal consistency with low inference cost. The framework introduces a Unified Unidirectional Latent Compressor, a Video DiT-based One-Step Diffusion Enhancer, and a Hybrid Condition Generator to efficiently compress latent slices and perform single-step spatio-temporal enhancement. Experiments on standard benchmarks confirm its performance.", "body_md": "arXiv:2608.20515v1 Announce Type: new\nAbstract: Generative video compression can recover rich visual details at low bitrates, but simultaneously achieving high temporal consistency and low inference cost remains challenging. To address this issue, we propose DiffVC-ONE, a diffusion-based generative video compression framework built on a one-step Video Diffusion Transformer. First, we introduce a Unified Unidirectional Latent Compressor that uses a shared model to efficiently and uniformly compress compact latent slices. We then develop a Video DiT-based One-Step Diffusion Enhancer that uses the reconstructed latent slices as content anchors and performs single-step spatio-temporal perceptual enhancement over an entire group of pictures. Finally, a Hybrid Condition Generator extracts structural, strength, and semantic conditions from the reconstructed content and quantization information. These conditions preserve faithful regions, control the degree of generative enhancement, and supplement content-aware perceptual details during one-step diffusion enhancement. Extensive experiments on multiple standard benchmarks demonstrate that DiffVC-ONE achieves state-of-the-art perceptual quality and temporal consistency with low inference cost.", "url": "https://wpnews.pro/news/diffvc-one-diffusion-based-generative-video-compression-with-one-step-video", "canonical_source": "https://arxiv.org/abs/2608.20515", "published_at": "2026-08-24 04:00:00+00:00", "updated_at": "2026-08-24 04:16:32.743899+00:00", "lang": "en", "topics": ["generative-ai", "artificial-intelligence", "machine-learning"], "entities": ["DiffVC-ONE", "Video Diffusion Transformer", "Unified Unidirectional Latent Compressor", "Video DiT-based One-Step Diffusion Enhancer", "Hybrid Condition Generator"], "alternates": {"html": "https://wpnews.pro/news/diffvc-one-diffusion-based-generative-video-compression-with-one-step-video", "markdown": "https://wpnews.pro/news/diffvc-one-diffusion-based-generative-video-compression-with-one-step-video.md", "text": "https://wpnews.pro/news/diffvc-one-diffusion-based-generative-video-compression-with-one-step-video.txt", "jsonld": "https://wpnews.pro/news/diffvc-one-diffusion-based-generative-video-compression-with-one-step-video.jsonld"}}