DiffVC-ONE: Diffusion-based Generative Video Compression with One-Step Video Diffusion Transformer

• URL: http://arxiv.org/abs/2608.20515v1
• Date: Thu, 20 Aug 2026 19:20:05 GMT
• Title: DiffVC-ONE: Diffusion-based Generative Video Compression with One-Step Video Diffusion Transformer
• Abstract summary: Generative video compression can recover rich visual details at lows, but simultaneously achieving high temporal consistency and low inference cost remains challenging.<n>We propose DiffVC-ONE, a diffusion-based generative video compression framework built on a one-step Video Transformer.<n>Experiments on multiple standard benchmarks demonstrate that DiffVC-ONE achieves perceptual state-of-theart perceptual quality and temporal consistency with low inference cost.
• Score: 38.495966630021556
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Efficient Video Diffusion with Sparse Information Transmission for Video Compression [24.272279529510772]
  Video compression aims to maximize reconstruction quality with minimal distortions.<n>At ultra-lows, traditional end-to-end compression models tend to produce blurry images of poor quality.<n>We propose Diff-SIT to establish a new state-of-the-art in perceptual quality and temporal consistency.
  arXiv  Detail & Related papers  (2026-03-19T05:15:29Z)
• MTC-VAE: Multi-Level Temporal Compression with Content Awareness [54.85288415164888]
  Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations.<n>We present a technique to convert fixed compression rate VAEs into models that support multi-level temporal compression.
  arXiv  Detail & Related papers  (2026-02-01T17:08:02Z)
• DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework [45.134271969594614]
  We first propose DiffVC-OSD, a One-Step Diffusion-based Perceptual Neural Video Compression framework.<n>We employ an End-to-End Finetuning strategy to improve overall compression performance.
  arXiv  Detail & Related papers  (2025-08-11T06:59:23Z)
• Conditional Video Generation for High-Efficiency Video Compression [48.32125957038998]
  We propose a video compression framework that leverages conditional diffusion models for perceptually optimized reconstruction.<n>Specifically, we reframe video compression as a conditional generation task, where a generative model synthesizes video from sparse, yet informative signals.
  arXiv  Detail & Related papers  (2025-07-21T06:16:27Z)
• REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder [52.698595889988766]
  We present a novel perspective on learning video embedders for generative modeling.<n>Rather than requiring an exact reproduction of an input video, an effective embedder should focus on visually plausible reconstructions.<n>We propose replacing the conventional encoder-decoder video embedder with an encoder-generator framework.
  arXiv  Detail & Related papers  (2025-03-11T17:51:07Z)
• Rethinking Video Tokenization: A Conditioned Diffusion-based Approach [58.164354605550194]
  New tokenizer, Diffusion Conditioned-based Gene Tokenizer, replaces GAN-based decoder with conditional diffusion model.<n>We trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch.<n>Even a scaled-down version of CDT (3$times inference speedup) still performs comparably with top baselines.
  arXiv  Detail & Related papers  (2025-03-05T17:59:19Z)
• Learned Video Compression via Heterogeneous Deformable Compensation Network [78.72508633457392]
  We propose a learned video compression framework via heterogeneous deformable compensation strategy (HDCVC) to tackle the problems of unstable compression performance. More specifically, the proposed algorithm extracts features from the two adjacent frames to estimate content-Neighborhood heterogeneous deformable (HetDeform) kernel offsets. Experimental results indicate that HDCVC achieves superior performance than the recent state-of-the-art learned video compression approaches.
  arXiv  Detail & Related papers  (2022-07-11T02:31:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.