Context-Aware Automatic Occlusion Removal
It addresses a generic, context-aware occlusion removal problem for image enhancement, which is incremental as it builds on existing domain-specific methods.
The paper tackles the problem of automatic occlusion removal by identifying objects unrelated to the image context as occlusions and removing them through inpainting, achieving a baseline performance on the COCO-Stuff dataset with user study validation.
Occlusion removal is an interesting application of image enhancement, for which, existing work suggests manually-annotated or domain-specific occlusion removal. No work tries to address automatic occlusion detection and removal as a context-aware generic problem. In this paper, we present a novel methodology to identify objects that do not relate to the image context as occlusions and remove them, reconstructing the space occupied coherently. The proposed system detects occlusions by considering the relation between foreground and background object classes represented as vector embeddings, and removes them through inpainting. We test our system on COCO-Stuff dataset and conduct a user study to establish a baseline in context-aware automatic occlusion removal.