Additive manufacturing (AM) is a new paradigm in design-driven build of customized products. Nonetheless, mass customization and low volume production make the AM quality assurance extremely challenging. Advanced imaging provides an unprecedented opportunity to increase information visibility, cope with the product complexity, and enable on-the-fly quality control in AM. However, in-situ images of a customized AM build show a high level of layer-to-layer geometry variation, which hampers the use of powerful image-based learning methods such as deep neural networks (DNNs) for flaw detection. Few, if any, previous works investigated how to tackle the impact of AM customization on image-guided process monitoring and control. The proposed research is aimed at filling this gap by developing a novel real-time and multi-scale process monitoring methodology for quality control of customized AM builds. Specifically, we leverage the computer-aided design (CAD) file to perform shape-to-image registration and delineate the regions of interests in lay-erwise images. Next, a hierarchical dyadic partitioning methodology is developed to split layer-to-layer regions of interest into subregions with the same number of pixels to provide freeform geometry analysis. Then, we propose a semiparametric model to characterize the complex spatial patterns in each customized subregion and boost the computational speed. Finally, a DNN model is designed to learn and detect fine-grained information of flaws. Experimental results show that the proposed process monitoring and control methodology detects flaws in each layer with an accuracy of 92.50±1.03%. This provides an opportunity to reduce inter-layer variation in AM prior to completion of the build. The proposed methodology can also be generally applicable in a variety of engineering and medical domains that entail image-based process monitoring and control with customized designs.