English

Incorporating Depth into both CNN and CRF for Indoor Semantic Segmentation

Computer Vision and Pattern Recognition 2018-07-30 v4

Abstract

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). First, a DFCN architecture which fuses depth information into the early layers and applies dilated convolution for later contextual reasoning is designed. Then, a depth-sensitive fully-connected conditional random field (DCRF) is proposed and combined with the previous DFCN to refine the preliminary result. Comparative experiments show that the proposed DFCN-DCRF has the best performance compared with most state-of-the-art methods.

Keywords

Cite

@article{arxiv.1705.07383,
  title  = {Incorporating Depth into both CNN and CRF for Indoor Semantic Segmentation},
  author = {Jindong Jiang and Zhijun Zhang and Yongqian Huang and Lunan Zheng},
  journal= {arXiv preprint arXiv:1705.07383},
  year   = {2018}
}

Comments

Accepted by IEEE ICSESS

R2 v1 2026-06-22T19:53:41.183Z