8 code implementations • 4 Jun 2018 • Jindong Jiang, Lunan Zheng, Fei Luo, Zhijun Zhang
Indoor semantic segmentation has always been a difficult task in computer vision.
Ranked #26 on Semantic Segmentation on SUN-RGBD (using extra training data)
no code implementations • 21 May 2017 • Jindong Jiang, Zhijun Zhang, Yongqian Huang, Lunan Zheng
To improve segmentation performance, a novel neural network architecture (termed DFCN-DCRF) is proposed, which combines an RGB-D fully convolutional neural network (DFCN) with a depth-sensitive fully-connected conditional random field (DCRF).