To address these issues, we propose a framework for the generation of breast ultrasound image-mask pairs based on the diffusion model. Specifically, in order to generate realistic breast ultrasound ...

MFTF enables precise control over object spatial positions without the need for additional masks, reference images, or model training and fine-tuning. The model supports single-object and multi-object ...

To address the above issues, we propose a novel edge-and-mask integration-driven diffusion model (EMidDiff). Specifically, 1) an edge-and-mask condition strategy is proposed for the segmentation ...

To solve these issues, we propose a mask diffusion-based contrastive learning method for knowledge-aware recommendation. Specifically, we apply local masked input to the diffusion model, using a mask ...

During the diffusion process, the model fuses the 3D adjacency information by adding an individual position map encoder to the pretrained image diffusion model. The new encoder resembles the design of ...