Perceptual Image Codec: What Matters in Practical Learned Image Compression

2026-05-24 | original

read original get Learned Image Compression Codec → more articles

Why This Matters

PICO (Perceptual Image Codec) represents a significant advancement in learned image compression by optimizing for human visual perception and practical on-device performance. Its substantial bitrate savings and fast processing times make it highly relevant for both consumers and the tech industry, enabling more efficient storage and transmission of high-quality images across devices. The codec's robustness and speed demonstrate the potential for widespread adoption of perceptually optimized compression technologies in everyday applications.

Key Takeaways

PICO achieves 2.3-3× bitrate savings over standards like AV1 and JPEG-AI.
It encodes 12MP images in approximately 230ms on an iPhone 17 Pro Max.
The codec offers cross-platform robustness and faster performance than many ML-based codecs.

We introduce PICO (Perceptual Image Codec) — the first learned codec that is both practical, and optimized directly for the human visual system. To derive it, we perform a comprehensive study of modeling choices for practical learned codecs, and search over millions of model configurations to jointly optimize over perceptual quality and on-device runtime.

Based on large-scale subjective user studies, PICO provides 2.3-3× bitrate savings against AV1, AV2, VVC, ECM and JPEG-AI, and 20-40% bitrate savings against the best learned codec alternatives. At the same time, on an iPhone 17 Pro Max, it encodes 12MP images as fast as 230ms, and decodes them in 150ms — faster than most top ML-based codecs run on a V100 GPU. Different from most learned codecs, PICO furthermore comes with cross-platform robustness guarantees.

PICO (Ours)

Explore topics: perceptual image codec av1 iphone 17 pro max learned codec human visual system