实用学习型图像压缩中真正重要的因素
What Matters in Practical Learned Image Compression
论文把感知质量与端侧运行时延作为联合优化目标，并用数百万骨干网络配置的感知性能神经架构搜索来寻找帕累托前沿，这套「感知指标驱动的 NAS + 时延约束」流程可直接迁移到超分、去噪等底层视觉模型的端侧部署设计。
原文依据 we perform performance-aware neural architecture search over millions of backbone configurations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论学习型编解码器相对于硬编码的传统编解码器所释放出的主要差异之一，在于它们能够直接针对人类视觉系统的偏好进行优化。尽管具备这一潜力，兼具感知性与实用性的图像编解码器仍未被提出。在本工作中，我们旨在弥合这一差距。我们对决定实用学习型图像编解码器设计的关键建模选择进行了全面研究，并同时针对感知质量与运行时进行联合优化，其中在消融实验中还纳入了若干新技术。随后，我们对数百万种骨干网络配置执行性能感知的神经架构搜索，以识别出在实现目标端侧运行时的同时、最大化以感知指标衡量的压缩性能的模型。我们将各项优化结合起来，构建出一个新的编解码器，在速度与感知质量之间取得了显著改善的权衡。基于严格的的主观用户研究，它相较 AV1、AV2、VVC、ECM 和 JPEG-AI 可实现 2.3–3 倍的码率节省，相较最佳的学习型编解码器方案可实现 20–40% 的码率节省。与此同时，在 iPhone 17 Pro Max 上，它编码 1200 万像素图像最快仅需 230 毫秒，解码仅需 150 毫秒——比大多数顶级基于机器学习的编解码器在 V100 GPU 上运行还要快。
英文原文摘要 1297 字符
One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet practical image codec is yet to be proposed.In this work, we aim to close this gap. We conduct a comprehensive study of the key modeling choices that govern the design of a practical learned image codec, jointly optimized for perceptual quality and runtime -- including within the ablations several novel techniques. We then perform performance-aware neural architecture search over millions of backbone configurations to identify models that achieve the target on-device runtime while maximizing compression performance as captured by perceptual metrics. We combine the various optimizations to construct a new codec that achieves a significantly improved tradeoff between speed and perceptual quality. Based on rigorous subjective user studies, it provides 2.3-3x 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.