Classical lens design minimizes optical aberrations to produce sharp images, but is typically decoupled from downstream computer vision tasks. Existing end-to-end optical design learns optical encoding through joint optimization, but often suffers from an unstable training process. We propose task-driven lens design, a new optimization philosophy for joint optics-network systems. We freeze the pretrained vision model and optimize only the lens so that the image formation better fits the model's feature preferences. This network-frozen setting yields a low-dimensional and stable optimization process, enabling lens design from scratch without human intervention, thereby exploring a broader design space. Multiple computer vision experiments show that TaskLenses outperform classical ImagingLenses with the same or even fewer elements. Our analysis reveals that the learned optics exhibit long-tailed point spread functions, better preserving preferred structural cues when aberrations cannot be fully corrected. These results highlight task-driven design as a practical route for optical lenses that are compatible with modern vision models, and also inspire new optical design objectives beyond traditional aberration minimization.

翻译：传统镜头设计通过最小化光学像差来生成清晰图像，但通常与下游计算机视觉任务相分离。现有的端到端光学设计通过联合优化学习光学编码，但常面临训练过程不稳定的问题。我们提出任务驱动的镜头设计，这是一种面向光学-网络联合系统的新型优化范式。我们冻结预训练的视觉模型，仅优化镜头参数，使成像过程更好地适配模型的特征偏好。这种网络冻结设置产生了低维且稳定的优化过程，能够实现无需人工干预的从零开始镜头设计，从而探索更广阔的设计空间。多项计算机视觉实验表明，TaskLenses在相同甚至更少镜片数量的情况下，性能优于传统成像镜头。我们的分析表明，学习得到的光学系统呈现出长尾点扩散函数，在无法完全校正像差时能更好地保留模型偏好的结构线索。这些结果凸显了任务驱动设计作为光学镜头与现代视觉模型兼容的实用路径，同时也启发了超越传统像差最小化的新型光学设计目标。