Corpus ID: 189762113

Training Image Estimators without Image Ground-Truth

@inproceedings{Xia2019TrainingIE,
  title={Training Image Estimators without Image Ground-Truth},
  author={Zhihao Xia and Ayan Chakrabarti},
  booktitle={NeurIPS},
  year={2019}
}
Deep neural networks have been very successful in image estimation applications such as compressive-sensing and image restoration, as a means to estimate images from partial, blurry, or otherwise degraded measurements. [...] Key Method We demonstrate that our framework can be applied for both regular and blind image estimation tasks, where in the latter case parameters of the measurement model (e.g., the blur kernel) are unknown: during inference, and potentially, also during training. We evaluate our method…Expand
3 Citations
Generative Patch Priors for Practical Compressive Image Recovery
  • PDF
Progressive Semantic Face Deblurring
  • 1
  • Highly Influenced
  • PDF
Unsupervised Image Restoration Using Partially Linear Denoisers
  • Rihuan Ke, C. Schönlieb
  • Medicine, Engineering
  • IEEE transactions on pattern analysis and machine intelligence
  • 2021
  • Highly Influenced
  • PDF

References

SHOWING 1-10 OF 36 REFERENCES
Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior
  • 21
  • PDF
Learning Intrinsic Image Decomposition from Watching the World
  • Z. Li, Noah Snavely
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
  • 77
  • PDF
Unsupervised Learning with Stein's Unbiased Risk Estimator
  • 31
  • PDF
Single Image Intrinsic Decomposition Without a Single Intrinsic Image
  • 27
  • PDF
ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements
  • 273
  • Highly Influential
  • PDF
Unsupervised Monocular Depth Estimation with Left-Right Consistency
  • 1,318
  • PDF
Fields of Experts
  • 631
  • PDF
From learning models of natural image patches to whole image restoration
  • 1,059
  • PDF
ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
  • J. Zhang, Bernard Ghanem
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
  • 172
  • Highly Influential
  • PDF
One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models
  • 208
  • PDF
...
1
2
3
4
...