CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
arXiv:2102.05181
Abstract
We propose Coordinate-based Internal Learning (CoIL) as a new deep-learning (DL) methodology for the continuous representation of measurements. Unlike traditional DL methods that learn a mapping from the measurements to the desired image, CoIL trains a multilayer perceptron (MLP) to encode the complete measurement field by mapping the coordinates of the measurements to their responses. CoIL is a self-supervised method that requires no training examples besides the measurements of the test object itself. Once the MLP is trained, CoIL generates new measurements that can be used within a majority of image reconstruction methods. We validate CoIL on sparse-view computed tomography using several widely-used reconstruction methods, including purely model-based methods and those based on DL. Our results demonstrate the ability of CoIL to consistently improve the performance of all the considered methods by providing high-fidelity measurement fields.
References in corpus (20)
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Image reconstruction by domain transform manifold learning
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- NeRF++: Analyzing and Improving Neural Radiance Fields
- Model based learning for accelerated, limited-view 3D photoacoustic tomography
- Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference Data
- Compressed Sensing using Generative Models
- Plug and play methods for magnetic resonance imaging (long version)
- An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
- RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
- On the Spectral Bias of Neural Networks
- Efficient and accurate inversion of multiple scattering with deep learning
- J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction
- Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
- Dense Recurrent Neural Networks for Accelerated MRI: History-Cognizant Unrolling of Optimization Algorithms
- SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors
- Regularized Fourier Ptychography using an Online Plug-and-Play Algorithm
- SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
- Robust Compressed Sensing using Generative Models