cs.CVNov 5, 2026

Neural Image Compression with Internal-External Prior Fusion and Alignment

Authors: Tiancheng Si, Wenlong Xu, Dahua Gao

Organizations: School of Artificial Intelligence, Xidian University, Xi’an 710126, China

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.

Figures & tables

Explore similar work

CardsList
  1. HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression

    Mar 6, 2026Haoxuan Xiong, Yuanyuan Xu, Kun Zhu +2Learned Image CompressionEntropy Coding

  2. ARCHE: Autoregressive Residual Compression with Hyperprior and Excitation

    Mar 10, 2026Sofia Iliopoulou, Dimitris Ampeliotis, Athanassios SkodrasLearned Image CompressionAutoregressive Modeling