A research team led by Prof. WANG Wencheng from the Institute of Software of the Chinese Academy of Sciences proposed a new method for image composition of partially occluded objects. The study was presented in Pacific Graphics 2019 and published in Computer Graphics Forum. 

Image composition tries to blend some contents of the source image into the target image seamlessly. Existing methods always require the contents from the source image must be placed over the contents of the target image.

It's difficult for these methods to blend the contents that are occluded partially by the contents of the target image, which always requires the user to interactively remove the occlude portions, or carefully order the contents before composition. This seriously prevents image composition efficiency. 

The researchers observed that the contents from the source image must be presented enough in the composited image, and in image composition, the contents from the source image were always placed to be on a plane that were shared by many contents of the target image.

Based on the observation, they developed novel measures that could well deduce the occlusion relationships between the contents from the source image and the contents of the target image, and proposed a new method that could efficiently perform image composition of partially occluded objects.

They employed learning-based methods to segment the objects in the source image and the target image, and obtain the depth information of the target image, and then allowed the user to select contents from the source image by simple interactivities, such as only clicking his interested objects.

After the user places his selected contents into the target image, the new method can well deduce the corresponding occlusion relationships between the contents from the source image and the target image, and perform image composition quickly.

As the new method avoids the limit that the contents from the source image must be placed over the contents of the target image, it considerably promotes image composition.