arXiv cs.AI· Tiancheng Si, Wenlong Xu, Dahua Gao·· 12 小时前AI 评分20
IE-PFA：融合内外先验的图像压缩模型，BD-Rate 较 VTM-22.0-Intra 节省 21.65%
Neural Image Compression with Internal-External Prior Fusion and Alignment
AI 导读
研究者提出 Internal-External Prior Fusion-Alignment（IE-PFA）上下文模型，用编解码器共享的可学习字典作为外部先验，并通过基于 RWKV 的 RSCPF 模块以线性复杂度融合内外先验。
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