AFP-GIC Cuts Generative Image Codec Latency 18.1% and Params 20.5% vs DC-VIC
SantaClaraUniversity · hf · 2026-10-07
Researchers from Santa Clara University propose AFP-GIC, a controllable generative image codec targeting the very-low-bitrate regime where learned codecs lose fine textures. The method transfers an adaptive fused prior from a frozen pretrained AdaCode model: encoder-side fused-prior features guide latent formation, while the decoder predicts a compatible fused prior from the compressed representation and control variables, avoiding transmission of the prior itself. A theoretical analysis shows better decoder-side prior alignment tightens the reconstruction-error upper bound, and the fused-prior family subsumes single-codebook designs. Against DC-VIC, AFP-GIC achieves 18.1% lower decoder latency and 20.5% fewer inference parameters (31.10M), with competitive PSNR/SSIM on Kodak, CLIC2020, and DIV2K and the clearest gains in NIQE and very-low-bitrate visual quality.
More from Research
- Self-improving agent Steve masters Minecraft unaided, out-progressing 97% of human players — julianweisser · 2026-10-07
- LLM2Vec-Gen: frozen LLMs generate answer embeddings in one forward pass, SOTA self-supervised — sivareddyg · 2026-10-07
- Researchers pitch World Editing: modifying existing worlds instead of generating new ones — yuntiandeng · 2026-10-07
- New paper asks: when agents act for you, whose side are they on? — ZacharyHuang12 · 2026-10-07
- AI's Top 10 research list: Spurious Rewards tops RL-heavy ranking — ShayneRedford · 2026-10-07
- SciConBench Team to Rerun Evaluations Every Two Months, Seeks Funding — manoelribeiro · 2026-10-07