Awesome

3DGNN for RGB-D segmentation

This is the Pytorch implementation of 3D Graph Neural Networks for RGBD Semantic Segmentation:

Data Preparation

1. Download NYU_Depth_V2 dataset from here and select scenes and save as ./datasets/data/nyu_depth_v2_labeled.mat
2. Transfer depth images to hha by yourself from here and save in ./datasets/data/hha/.

Emviroment

Required CUDA (8.0) + pytorch 0.4.1