OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation
Researchers have developed OcclusionFormer, a new framework designed to improve image generation models by explicitly handling object occlusion. This is achieved by introducing a Z-order priority system and utilizing volume rendering to composite instances. The framework is supported by a new dataset, SA-Z, which includes detailed occlusion ordering and pixel-level annotations to train and evaluate the model's ability to manage overlapping objects. AI
IMPACT Improves image generation by enabling models to accurately represent object layering and occlusion.