用视频扩散模型预测下一帧，实现超低码率图像压缩。
Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors
- 解码时先生成语义清晰的锚帧，再用扩散模型逐步重建图像。
- 在CLIC2020上相比DiffC降低50%以上码率，且加速达5倍。
- 适合追求高画质与高速解码的超低码率压缩场景。
我们提出一种利用生成式图像压缩中时间演化的新型超低码率图像压缩（ULB-IC）范式。具体而言，在解码过程中定义了一个显式的中间状态：一个保留场景几何与语义布局但舍弃高频细节的紧凑锚帧。随后将生成解码重释为从该锚帧到最终重建图像的虚拟时间演化过程。为此，我们借助预训练视频扩散模型（VDM）作为时间先验：以锚帧为初始帧，原图为目标帧，将解码转化为下一帧预测任务。相较于基于图像扩散的ULB-IC模型，我们的方法从一个可见且语义忠实的锚帧开始，提升了感知质量与真实感。大量实验表明，本方法在率失真性能上表现优异。在CLIC2020测试集上，相比DiffC，LPIPS、DISTS、FID和KID指标下码率降低超过50%，同时解码速度提升高达5倍。代码将发布于https://github.com/UnoC-727/NeFIC。
原文摘要 · Abstract (English)
We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the ``temporal'' evolution in generative image compression. Specifically, we define an explicit intermediate state during decoding: a compact anchor frame, which preserves the scene geometry and semantic layout while discarding high-frequency details. We then reinterpret generative decoding as a virtual temporal transition from this anchor to the final reconstructed image. To model this progression, we leverage a pretrained video diffusion model (VDM) as a temporal prior: the anchor frame serves as the initial frame and the original image as the target frame, transforming the decoding process into a next-frame prediction task. In contrast to image diffusion-based ULB-IC models, our decoding proceeds from a visible, semantically faithful anchor, which improves both fidelity and realism for perceptual image compression. Extensive experiments demonstrate that our method achieves superior rate-distortion performance. On the CLIC2020 test set, our method achieves over 50% bitrate savings across LPIPS, DISTS, FID, and KID compared to DiffC, while also delivering a significant decoding speedup of up to $\times$5. Code will be released at https://github.com/UnoC-727/NeFIC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。