Scene Intrinsics and Depth from a Single Image

作者: Evan Shelhamer , Jonathan T. Barron , Trevor Darrell

DOI: 10.1109/ICCVW.2015.39

关键词:

摘要: Intrinsic image decomposition factorizes an observed into its physical causes. This is most commonly framed as a reflectance and shading, although recent progress has made full decompositions shape, illumination, reflectance, shading possible. However, existing factorization approaches require depth sensing to initialize the optimization of scene intrinsics. Rather than relying on sensors, we show that estimated purely from monocular appearance can provide sufficient cues for intrinsic analysis. Our pipeline regresses by fully convolutional network then jointly optimizes recover input image. combination yields uniting feature learning through deep regression with modeling statistical priors random field regularization. work demonstrates first scenes single color alone.

参考文章(31)
H. G. Barrow, J. M. Tenenbaum, RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES ,(1978)
Nathan Silberman, Derek Hoiem, Pushmeet Kohli, Rob Fergus, Indoor Segmentation and Support Inference from RGBD Images Computer Vision – ECCV 2012. pp. 746- 760 ,(2012) , 10.1007/978-3-642-33715-4_54
Peter N. Belhumeur, David J. Kriegman, Alan L. Yuille, The Bas-Relief Ambiguity International Journal of Computer Vision. ,vol. 35, pp. 33- 44 ,(1999) , 10.1023/A:1008154927611
Andrew Paul Witkin, Shape from Contour Massachusetts Institute of Technology. ,(1980)
Berthold KP Horn, SHAPE FROM SHADING: A METHOD FOR OBTAINING THE SHAPE OF A SMOOTH OPAQUE OBJECT FROM ONE VIEW Massachusetts Institute of Technology. ,(1970)
Pushmeet Kohli, Joshua B. Tenenbaum, Tejas D. Kulkarni, William F. Whitney, Deep convolutional inverse graphics network neural information processing systems. ,vol. 28, pp. 2539- 2547 ,(2015)
Fayao Liu, Chunhua Shen, Guosheng Lin, Ian Reid, Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 38, pp. 2024- 2039 ,(2016) , 10.1109/TPAMI.2015.2505283
Geoffrey E. Hinton, Ruslan Salakhutdinov, Yichuan Tang, Deep Lambertian Networks international conference on machine learning. pp. 1419- 1426 ,(2012)
Saurabh Gupta, Pablo Arbelaez, Ross Girshick, Jitendra Malik, Aligning 3D models to RGB-D images of cluttered scenes computer vision and pattern recognition. pp. 4731- 4740 ,(2015) , 10.1109/CVPR.2015.7299105
Berthold K.P. Horn, Determining lightness from an image Computer Graphics and Image Processing. ,vol. 3, pp. 277- 299 ,(1974) , 10.1016/0146-664X(74)90022-7