Neural Image Compression with Internal-External Prior Fusion and Alignment
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
| Method | BD-Rate over VTM-22.0-Intra (%) | GFLOPs | Params | Enc. | Dec. | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Kodak | CLIC | Tecnick | HEVC B | HEVC C | HEVC D | HEVC E | AVG | (ms) | (ms) | |||
| VTM-22.0-Intra | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | – | – | – | – |
| ELIC [ 12 ] | 371 | 41.9M | 91 | 119 | ||||||||
| STF [ 30 ] | 304 | 99.8M | 102 | 131 | ||||||||
| TCM [ 13 ] | 701 | 75.9M | 142 | 151 | ||||||||
| DCVC-DC-Intra [ 31 ] | 278 | 31.0M | 78 | 66 | ||||||||
| Method | BD-Rate |
|---|---|
| Baseline | |
| + RSCPF | |
| + Dictionary | |
| + SDPA | |
| DCAE [ 7 ] | |
| + SDPA |
Learned Image Compression
Learned image compression uses neural encoders, quantization, and entropy models to reduce image bitrates while balancing fidelity, perceptual quality, and task utility.
See all 135 papers