Performance Enhanced Elemental Array Generation for Integral Image Display Using Pixel Fusion

Integral imaging is an emerging three-dimensional display technology. However, some inherent issues such as depth inversion has restricted its development. As such, this paper proposes a pixel fusion technique to generate elemental image arrays and overcome pseudoscopic problems occurring in sparse imaging environments. The similarity between the aimed displayed rays and the two adjacent captured rays of an object in a parallel light field was measured by the ratio of the spatial distance of the displayed and captured rays to the interval of the adjacent captured light. Displayed pixel values were acquired for the parallel captured rays. Corresponding pixel position errors were determined in sparse capture conditions and the method was further improved by using the position errors to identify the correct pixel, resulting in higher image quality. The proposed technique does not require manual adjustment of reference planes or other parameters, even at low capturing densities. This provides added convenience and may reduce capturing costs in actual scenes. Experiments using two bricks in virtual scenes under 9 x 9 to 137 x 137 capture cameras were conducted, and the quality of the generated elemental image array was compared with smart pseudoscopic-to-orthoscopic conversion (SPOC). The peak signal-to-noize ratio (PSNR) and structural similarity (SSIM) values showed the effectiveness of the proposed technique. The optical reconstruction results from both real and virtual scenes demonstrated improvements in vision of reconstructed three-dimensional scenes.