基于内外先验融合与对齐的神经图像压缩模型 IE-PFA
Neural Image Compression with Internal-External Prior Fusion and Alignment
AI 导读
研究者提出内外先验融合对齐（IE-PFA）上下文模型，用于学习式图像压缩，通过可共享字典作外部先验弥补现有上下文模型仅依赖当前图像内部先验的不足。模型基于四叉树空间-通道联合建模，RWKV 模块的 RSCPF 以线性复杂度融合先验，训练阶段的 SDPA 对齐机制不增加推理开销，支持 64 个质量级别的单网络变码率编码。
正文 · 原文
Abstract:Existing context models for learned image com- pression rely primarily on internal priors from the current image, overlooking common patterns and typical textures shared across natural images. To address this limitation, we propose an Internal-External Prior Fusion-Alignment (IE-PFA) context model built upon quadtree spatial-channel joint modeling, where a learnable dictionary shared by the encoder and decoder serves as an external prior. Specifically, an RWKV-based Spatial- Channel Prior Fusion (RSCPF) module efficiently fuses inter- nal and external priors along spatial and channel dimensions with linear complexity, while a training-only Self-Distilled Prior Alignment (SDPA) mechanism aligns them without inference overhead. Moreover, our model supports variable-rate coding over 64 quality levels within a single network and is accelerated by custom CUDA operators. Experiments on seven benchmarks demonstrate state-of-the-art rate-distortion performance, achiev- ing an average BD-Rate saving of 21.65% over VTM-22.0-Intra, with only 29.9M parameters and the fastest coding speed among advanced neural codecs (61 ms encoding and 52 ms decoding). Code is available at this https URL.
| Comments: | IEEE International Conference on Visual Communications and Image Processing 2026 (VCIP 2026) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07644 [cs.CV] |
| (or arXiv:2611.07644v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07644 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tiancheng Si [view email]
[v1]
Thu, 5 Nov 2026 08:27:45 UTC (657 KB)
来源：arXiv cs.AI · arxiv.org