arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.07541cs.CVcs.AIeess.IV
收藏

DifuzCam:用掩模与扩散模型替代相机镜头

DifuzCam: Replacing Camera Lens with a Mask and a Diffusion Model

Tel Aviv University(特拉维夫大学)

Erez Yosef, Raja Giryes

AI总结:

针对平面无镜头相机重建图像质量不佳的问题,提出结合带控制网络的预训练扩散模型与可学习可分离变换的重建方法,构建出成像质量与感知效果达SOTA的DifuzCam原型,还可结合文本描述增强重建,方法可推广至其他成像系统。

摘要:

平面无镜头相机设计可大幅降低相机的尺寸与重量。在该设计中,相机镜头被另一种可对入射光产生干涉作用的光学元件替代,图像通过重建算法从传感器原始测量值中恢复,但重建图像的质量仍不尽如人意。为解决这一问题,我们提出采用带有控制网络的预训练扩散模型,结合可学习的可分离变换来完成重建。基于该方法我们构建了一台可实现高质量成像的平面相机原型,在成像质量与感知效果两方面均取得了当前最优结果。我们还验证了该方法可结合拍摄场景的文本描述进一步提升重建效果。这种利用预训练扩散模型强大能力的重建方法,可应用于其他成像系统以提升重建效果。

英文摘要:

The flat lensless camera design reduces the camera size and weight significantly. In this design, the camera lens is replaced by another optical element that interferes with the incoming light. The image is recovered from the raw sensor measurements using a reconstruction algorithm. Yet, the quality of the reconstructed images is not satisfactory. To mitigate this, we propose utilizing a pre-trained diffusion model with a control network and a learned separable transformation for reconstruction. This allows us to build a prototype flat camera with high-quality imaging, presenting state-of-the-art results in both terms of quality and perceptuality. We demonstrate its ability to leverage also textual descriptions of the captured scene to further enhance reconstruction. Our reconstruction method which leverages the strong capabilities of a pre-trained diffusion model can be used in other imaging systems for improved reconstruction results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑