CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition

@article{Baslamisli2018CNNBL,
  title={CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition},
  author={Anil S. Baslamisli and Hoang-An Le and T. Gevers},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={6674-6683}
}
Most of the traditional work on intrinsic image decomposition rely on deriving priors about scene characteristics. [...] Key Method A method is proposed that (1) is empowered by deep learning capabilities, (2) considers a physics-based reflection model to steer the learning process, and (3) exploits the traditional approach to obtain intrinsic images by exploiting reflectance and shading gradient information. The proposed model is fast to compute and allows for the integration of all intrinsic components.Expand
34 Citations
Outdoor inverse rendering from a single image using multiview self-supervision
  • Ye Yu, W. Smith
  • Computer Science, Medicine
  • IEEE transactions on pattern analysis and machine intelligence
  • 2021
  • PDF
Single Image Intrinsic Decomposition with Discriminative Feature Encoding
  • Zongji Wang, Feng Lu
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
  • 2019
  • 4
  • Highly Influenced
  • PDF
Non-Local Intrinsic Decomposition With Near-Infrared Priors
  • 6
  • PDF
NIID-Net: Adapting Surface Normal Knowledge for Intrinsic Image Decomposition in Indoor Scenes
  • 1
  • PDF
Leveraging Multi-view Image Sets for Unsupervised Intrinsic Image Decomposition and Highlight Separation
  • PDF
Intrinsic image decomposition as two independent deconvolution problems
...
1
2
3
4
...

References

SHOWING 1-10 OF 45 REFERENCES
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression
  • 128
  • PDF
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
  • 135
  • PDF
Learning Non-Lambertian Object Intrinsics Across ShapeNet Categories
  • J. Shi, Yue Dong, H. Su, S. Yu
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
  • 98
  • Highly Influential
  • PDF
Learning Data-Driven Reflectance Priors for Intrinsic Image Decomposition
  • 112
  • PDF
A Simple Model for Intrinsic Image Decomposition with Depth Cues
  • 155
  • PDF
Estimating Intrinsic Component Images using Non-Linear Regression
  • M. Tappen, E. Adelson, W. Freeman
  • Mathematics, Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
  • 98
  • PDF
Estimation of Intrinsic Image Sequences from Image+Depth Video
  • 84
  • PDF
Learning lightness from human judgement on relative reflectance
  • 52
  • PDF
Intrinsic Scene Properties from a Single RGB-D Image
  • 117
  • PDF
...
1
2
3
4
5
...