Robust Room Layout Estimation from a Single Image with Geometric Hints
作者： Ruifeng Deng , Xuejin Chen
DOI: 10.1109/ICIP.2018.8451365
关键词:
摘要: Estimation of room layout suffers from heavy occlusions and clutters in indoor scenes. In this paper, we propose a deep network that combines textures geometric hints to predict the surface single image. Our method consists three steps. First, depths normals are extracted input RGB Secondly, multi-channel FCN (MC-FCN) is presented integrate these for semantic segmentation. Thirdly, an optimization framework adopted refine estimation. The results on two commonly used benchmark datasets demonstrate robustness our complex
sci-hub.se 参考文章(19)
Clément Farabet, Clément Farabet, Camille Couprie, Yann LeCun, Laurent Najman, Indoor Semantic Segmentation using depth information arXiv: Computer Vision and Pattern Recognition. ,(2013)
Saurabh Gupta, Ross Girshick, Pablo Arbeláez, Jitendra Malik, Learning Rich Features from RGB-D Images for Object Detection and Segmentation european conference on computer vision. pp. 345- 360 ,(2014) , 10.1007/978-3-319-10584-0_23
Varsha Hedau, Derek Hoiem, David Forsyth, Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry Computer Vision – ECCV 2010. pp. 224- 237 ,(2010) , 10.1007/978-3-642-15567-3_17
Jonathan Long, Evan Shelhamer, Trevor Darrell, Fully convolutional networks for semantic segmentation computer vision and pattern recognition. pp. 3431- 3440 ,(2015) , 10.1109/CVPR.2015.7298965
David Eigen, Rob Fergus, Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture 2015 IEEE International Conference on Computer Vision (ICCV). pp. 2650- 2658 ,(2015) , 10.1109/ICCV.2015.304
Huayan Wang, Stephen Gould, Daphne Roller, None, Discriminative learning with latent variables for cluttered indoor scene understanding Communications of the ACM. ,vol. 56, pp. 92- 99 ,(2013) , 10.1145/2436256.2436276
J.M. Coughlan, A.L. Yuille, Manhattan World: compass direction from a single image by Bayesian inference international conference on computer vision. ,vol. 2, pp. 941- 947 ,(1999) , 10.1109/ICCV.1999.790349
Abhinav Gupta, Martial Hebert, Takeo Kanade, David M. Blei, Estimating Spatial Layout of Rooms using Volumetric Reasoning about Objects and Surfaces neural information processing systems. ,vol. 23, pp. 1288- 1296 ,(2010)
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition computer vision and pattern recognition. pp. 770- 778 ,(2016) , 10.1109/CVPR.2016.90
Arun Mallya, Svetlana Lazebnik, Learning Informative Edge Maps for Indoor Scene Layout Prediction international conference on computer vision. pp. 936- 944 ,(2015) , 10.1109/ICCV.2015.113