In imaging inverse problems, we would like to know how close the recovered image is to the true image in terms of full-reference image quality (FRIQ) metrics like PSNR, SSIM, LPIPS, etc. This is especially important in safety-critical applications like medical imaging, where knowing that, say, the SSIM was poor could potentially avoid a costly misdiagnosis. But since we don't know the true image, computing FRIQ is non-trivial. In this work, we combine conformal prediction with approximate posterior sampling to construct bounds on FRIQ that are guaranteed to hold up to a user-specified error probability. We demonstrate our approach on image denoising and accelerated magnetic resonance imaging (MRI) problems. Code is available at https://github.com/jwen307/quality_uq.

翻译：在成像逆问题中，我们通常希望了解重建图像在诸如PSNR、SSIM、LPIPS等全参考图像质量（FRIQ）指标上距离真实图像有多近。这在医学成像等安全关键型应用中尤为重要，因为例如，若知道SSIM值较差，则可能避免代价高昂的误诊。然而，由于我们不知道真实图像，计算FRIQ并非易事。在本工作中，我们将保形预测与近似后验采样相结合，构建了FRIQ的界限，并保证该界限在用户指定的误差概率内成立。我们在图像去噪和加速磁共振成像（MRI）问题上验证了我们的方法。代码可在 https://github.com/jwen307/quality_uq 获取。