This study introduces a refined algorithm for creating artistic portraits with dynamic, editable lighting effects derived from facial photographs. The proposed method begins by extracting edge contours from the input photo to construct a foundational line drawing. Subsequent steps involve intrinsic decomposition to differentiate between the photo's illumination and reflectance components. The illumination component undergoes a series of edits, including quantization and nonlinear adjustments, to refine its visual impact. Concurrently, the reflectance component is abstracted and merged with the line drawing to form a preliminary cartoon-style image devoid of specific lighting effects. The final artistic rendering is achieved by reintegrating the edited illumination component, resulting in a visually striking cartoon image that preserves realistic lighting dynamics. Experimental evaluations confirm the algorithm's ability to produce high-quality, realistic cartoon images with customizable lighting effects, making it a significant contribution to the fields of non-photorealistic rendering and digital art creation.
No takes yet. Share an insight, caveat, or question.
Philip et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: