Sequential Amodal Segmentation via Cumulative Occlusion Learning
This addresses the need for robotic applications to handle objects of uncertain categories in densely layered scenes, though it is an incremental improvement over existing methods.
The paper tackles the problem of segmenting both visible and occluded regions of objects in single images to understand 3D context, introducing a diffusion model with cumulative occlusion learning that outperforms baselines on three amodal datasets.
To fully understand the 3D context of a single image, a visual system must be able to segment both the visible and occluded regions of objects, while discerning their occlusion order. Ideally, the system should be able to handle any object and not be restricted to segmenting a limited set of object classes, especially in robotic applications. Addressing this need, we introduce a diffusion model with cumulative occlusion learning designed for sequential amodal segmentation of objects with uncertain categories. This model iteratively refines the prediction using the cumulative mask strategy during diffusion, effectively capturing the uncertainty of invisible regions and adeptly reproducing the complex distribution of shapes and occlusion orders of occluded objects. It is akin to the human capability for amodal perception, i.e., to decipher the spatial ordering among objects and accurately predict complete contours for occluded objects in densely layered visual scenes. Experimental results across three amodal datasets show that our method outperforms established baselines.