ShapeConv, or Shape-aware Convolutional layer, is a convolutional layer for processing the depth feature in indoor RGB-D semantic segmentation. The depth feature is firstly decomposed into a shape-component and a base-component, next two learnable weights are introduced to cooperate with them independently, and finally a convolution is applied on the re-weighted combination of these two components.

Source: ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation


Paper Code Results Date Stars


Task Papers Share
Semantic Segmentation 1 50.00%
Thermal Image Segmentation 1 50.00%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign