Shape-Preserving Stereo Object Remapping via Object-Consistent Grid Warping

Viewing various stereo images under different viewing conditions has escalated the need for effective object-level remapping techniques. In this paper, we propose a new object spatial mapping scheme, which adjusts depth and size of selected to match user preference conditions. Existing warping-based methods often distort shape important objects or cannot faithfully adjust depth/size due improper warping such as local rotations. by explicitly reducing transformation freedom degree warping, an optimization model based on axis-aligned remapping. The proposed can simultaneously depths sizes their target values without introducing severe distortions. Moreover, consistency constraints ensure size/shape parts inside be consistently adjusted. Such improve adjustment performance while remaining robust some extent incomplete extraction. Experimental results demonstrate that method achieves high flexibility effectiveness in adjusting compared with existing methods.