Image processing of high-resolution, 3D images to create digital representations of pore micro-structures for Image-Based Rock Physics simulations remains a highly subjective enterprise despite the seemly precision associated with improving imaging resolutions and intensive parallel computations. The decisions on how to identify pore space, both macro- and micro-pores, and various mineral components remains very much dependent upon user choices and biases. Treatment of sub-resolution features, i.e., mineral facies with micro-porosity that are below the imaging resolution, is critical in tight reservoirs, but rarely included systematically in the analysis. A set of shaly-sand samples with a significant amount of authigenic chlorite/smectite that lines the larger pores was tested to identify uncertainty quantification (UQ) requirements associated with image-processing steps– segmentation in particular. Two segmentation strategies, conventional thresholding based and artificial intelligence (AI) based, are employed with different UQ parameter space. Relative proportions of macro- and micro-pores in these samples, and their spatial distributions with regard to pore-lining clay mineral, are iteratively studied over the defined UQ parameter space, and cross-validated by independent Nuclear Magnetic Resonance (NMR) measurements. The pore micro-structure extracted from these different iterations were the basis of simulations of basic petrophysical properties. Upon cross-validation with measured core properties, a UQ framework is proposed to assess the differences between the different measurements from three angles: sampling, numerical and physical.