Hyperparameter Analysis for Derivative Compressive Sampling
Derivative compressive sampling (DCS) is a signal reconstruction method from measurements of the spatial gradient with sub-Nyquist sampling rate. Applications of DCS include optical image reconstruction, photometric stereo, and shape-from-shading. In this work, we study the sensitivity of DCS with respect to algorithmic hyperparameters using a brute-force search algorithm. We perform experiments on a dataset of surface images and deduce guidelines for the user to setup values for the hyperparameters for improved signal recovery performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ReconstructionSensitivitySimilar Papers 제목 키워드 기반
Structurally Adaptive Multi-Derivative Regularization for Image Recovery from Sparse Fourier Samples
The importance of regularization has been well established in image reconstruction -- which is the computational inversion of imaging forward model -- with applications including deconvolution for microscopy, tomographic…
Compressive SensingImage ReconstructionExploiting gradients and Hessians in Bayesian optimization and Bayesian quadrature
An exciting branch of machine learning research focuses on methods for learning, optimizing, and integrating unknown functions that are difficult or costly to evaluate. A popular Bayesian approach to this problem uses a …
Bayesian OptimizationGaussian ProcessesOn Grid Compressive Sampling for Spherical Field Measurements in Acoustics
We derive a compressive sampling method for acoustic field reconstruction using field measurements on a predefined spherical grid that has theoretically guaranteed relations between signal sparsity, measurement number, a…
Compressive SensingDenoisingAutotune: A Derivative-free Optimization Framework for Hyperparameter Tuning
Machine learning applications often require hyperparameter tuning. The hyperparameters usually drive both the efficiency of the model training process and the resulting model quality. For hyperparameter tuning, machine l…
BIG-bench Machine LearningCompressive Sampling Using EM Algorithm
Conventional approaches of sampling signals follow the celebrated theorem of Nyquist and Shannon. Compressive sampling, introduced by Donoho, Romberg and Tao, is a new paradigm that goes against the conventional methods …