Paper reading: Conditional Diffusion for Interactive Segmentation ICCV2021

交互式语义分割

We propose Conditional Diffusion Network (CDNet), which propagates labeled representations
from clicks to conditioned destinations with two levels of affinities:

Feature Diffusion Module (FDM) spreads features from clicks to potential target regions with global similarity;
Pixel Diffusion Module (PDM) diffuses the predicted logits of clicks within locally connected regions.

定义起始的click区域，和diffusion目标区域，作为约束信息，交互进行diffusion。

 

把原始图像、click的高斯maps，和预测的逻辑值，作为输入，进而促进信息从点位置到邻近像素的传播和预测。