苹果推出首个实用感知图像编解码器
推荐指数 63.0 NO. 012 · 2026.05.25
发布2026/05/24Score61Comments20
为什么值得看
苹果发布PICO，首个针对人眼视觉系统直接优化的实用学习型图像编解码器，通过数百万模型配置搜索联合优化感知质量与端侧运行速度。相比AV1/AV2/VVC等传统标准实现2.3-3倍码率节省，对端侧图像传输和存储场景有显著价值。
媒体预览
编辑判断
图像压缩领域长期存在一个尴尬局面：学习型编解码器在学术指标上好看，但要么算力开销太大无法落地，要么优化的是PSNR/SSIM而非人眼实际观感。苹果这次用大规模主观实验替代客观指标来指导模型搜索，相当于把"人眼验收"写进了训练循环。
PICO直接对标JPEG-AI和ECM这些下一代标准，而且强调"on-device runtime"，暗示苹果很可能已经在Camera、Photos或Vision Pro的管线中部署。做端侧图像/视频处理的团队需要关注：如果苹果把这套方法扩展到视频（PICO-V），现有基于HEVC/AV1的流媒体架构可能面临重构压力。
论文和代码未完全开源，但技术报告已放出。做编解码器创业或硬件加速的团队，建议重点研究它的感知损失设计和模型搜索策略，而非复现完整模型。
社区反馈
意见分歧 20 条评论
核心争论：PICO 的纹理合成式压缩是感知优化还是语义失真，以及 150ms 解码延迟是否适合端侧场景
this is interesting. would be cool to explore something like integrating a vlm to add a "semantic" term to the loss function. looking through the comparisons, some of the baseline codecs create meaningfully different details (as could be described by text) in the images.
Looks very cool assuming all the comparisons are correct & fair and there’s no major failure cases. Quick link to the HTML version of the paper to save you a couple of clicks: https://arxiv.org/html/2605.05148v1 Since this is by Apple, I’m certainly curious if this is aimed at be
>what the BD acronym in “BD rate” stands for, Bjontegaard Delta-Rate (BD Rate) metric, proposed in 2001 by Gisle Bjontegaard, is a method for calculating the average difference between two rate-distortion (RD) curves. It is extremely common in codec comparison, along with terms like PSNR, SSIM and