NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning

arXiv:2604.03353v2 Announce Type: replace-cross 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 and on 24 HD sequences at 720p and 1080p (Xiph, UVG, and the modern BVI-AOM benchmark) show that NeuralLVC outperforms H.264 and H.265 lossless by a significant margin at every resolution tested. 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.

Related

• Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors
• Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
• Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising
• EvDiff: Event-Based Video Reconstruction using One-Step Diffusion Models

Source: arXiv cs.CV | 2026-09-09