# Neural Image Compression with Internal-External Prior Fusion and Alignment

**Authors:** Tiancheng Si, Wenlong Xu, Dahua Gao  
**Lab:** Xidian University · **Published:** 5 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.07644) · [PDF](https://arxiv.org/pdf/2611.07644) · [Code](https://github.com/stcnjtech/DCVC-X-Intra) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.07644.html)

## Key numbers

- **21.65%**: achiev- ing an average BD-Rate saving of 21.65% over VTM-22.0-Intra
- **29.9M**: with only 29.9M parameters and the fastest coding speed among advanced neural codecs

## 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 https://github.com/stcnjtech/DCVC-X-Intra.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.