Abstract
While neural lossless image compression has advanced significantly with learned entropy models, lossless video compression remains largely unexplored in the neural setting. We present NeuralLVC, a neural lossless video codec that combines masked diffusion with an I/P-frame architecture for exploiting temporal redundancy. Our I-frame model compresses individual frames using bijective linear tokenization that guarantees exact pixel reconstruction. The P-frame model compresses temporal differences between consecutive frames, conditioned on the previous decoded frame via a lightweight reference embedding that adds only 1.3% trainable parameters. Group-wise decoding enables controllable speed-compression trade-offs. Our codec is lossless in the input domain: for video, it reconstructs YUV420 planes exactly; for image evaluation, RGB channels are reconstructed exactly. Experiments on 9 Xiph CIF sequences show that NeuralLVC outperforms H.264 and H.265 lossless by a significant margin. We verify exact reconstruction through end-to-end encode-decode testing with arithmetic coding. These results suggest that masked diffusion with temporal conditioning is a promising direction for neural lossless video compression.
Abstract (translated)
尽管神经无损图像压缩已通过学习熵模型取得显著进展，但神经框架下的无损视频压缩仍 largely 未被探索。本文提出 NeuralLVC，一种结合掩码扩散与 I/P 帧架构的神经无损视频编解码器，用于利用时间冗余。其 I 帧模型通过双射线性分词压缩单帧，保证像素精确重建；P 帧模型则通过轻量级参考嵌入（仅增加 1.3% 可训练参数）对连续帧间的时间差进行压缩，并以已解码前一帧为条件。分组解码机制实现了可控的速度-压缩率权衡。该编解码器在输入域实现无损：视频场景下精确重建 YUV420 平面；图像评估场景下精确重建 RGB 通道。在 9 个 Xiph CIF 序列上的实验表明，NeuralLVC 显著优于 H.264 与 H.265 的无损模式。通过算术编码的端到端编解码测试验证了精确重建能力。这些结果表明，结合时间条件的掩码扩散是神经无损视频压缩的一个有前景的方向。
URL
https://arxiv.org/abs/2604.03353
