Image editing by object-aware optimal boundary searching and mixed-domain composition

Abstract

When combining very different images which often contain complex objects and backgrounds, producing consistent compositions is a challenging problem requiring seamless image editing. In this paper, we propose a general approach, called objectaware image editing, to obtain consistency in structure, color, and texture in a unified way. Our approach improves upon previous gradient-domain composition in three ways. Firstly, we introduce an iterative optimization algorithm to minimize mismatches on the boundaries when the target region contains multiple objects of interest. Secondly, we propose a mixeddomain consistency metric for measuring gradients and colors, and formulate composition as a unified minimization problem that can be solved with a sparse linear system. In particular, we encode texture consistency using a patch-based approach without searching and matching. Thirdly, we adopt an objectaware approach to separately manipulate the guidance gradient fields for objects of interest and backgrounds of interest, which facilitates a variety of seamless image editing applications. Our unified method outperforms previous state-of-the-art methods in preserving global texture consistency in addition to local structure continuity.

Deep Texture-Aware Features for Camouflaged Object Detection

“…We compare our method against 13 cutting-edge methods, including (1) FPN [20], (2) MaskRCNN [12], (3) PSP-Net [40], (4) UNet++ [43], (5) PiCANet [21], (6) MSR-CNN [14], (7) BASNet [26], (8) PFANet [42], (9) CPD [37], (10) HTC [2], (11) EGNet [41], (12)ANet-SRM [19], and (13) SINet [7]. Note that SINet has reported the quantitative results and released camouflaged object maps predicted by all compared COD methods.…”

“…Hence, camouflaged object detection [7] has been a great challenge and solving this problem could benefit a lot of applications in computer vision, such as polyp segmentation [8], lung infection segmentation [9,36], photo-realistic blending [11], and recreational art [4].…”

Deep Generation of Face Images from Sketches

“…Traditional copy-paste methods (e.g., [9]) use seamless stitching methods on colored images. However, there will be situations where the hue of local areas is irrelevant.…”

ShadowGAN: Shadow synthesis for virtual objects with conditional adversarial networks

“…Liu et al [4] estimated illumination and scene geometry from video for various video applications. Ge et al [12] proposed an object-aware image editing approach to obtain consistency in structure, color, and texture in a unified way. Rendering virtual objects into real scenes has been long investigated.…”