Computation times#
17:15.271 total execution time for 96 files from all galleries:
Example |
Time |
Mem (MB) |
|---|---|---|
Reducing the memory and computational complexity of unfolded network training ( |
02:09.468 |
0.0 |
Fitting NIQE on a custom dataset ( |
01:04.459 |
0.0 |
Inverse scattering problem ( |
00:59.426 |
0.0 |
Self-supervised learning with Equivariant Splitting ( |
00:58.833 |
0.0 |
Deep Equilibrium (DEQ) algorithms for image deblurring ( |
00:51.066 |
0.0 |
Blind deblurring with kernel estimation network ( |
00:41.332 |
0.0 |
Scan-specific zero-shot SSDU for MRI ( |
00:39.077 |
0.0 |
Reconstruct undersampled k-space for cardiac and brain MRI ( |
00:37.327 |
0.0 |
Vanilla Unfolded algorithm for super-resolution ( |
00:31.897 |
0.0 |
3D PET reconstruction with the Brainweb dataset ( |
00:31.715 |
0.0 |
Reconstruct prospectively-undersampled raw multicoil MRI ( |
00:30.987 |
0.0 |
Benchmarking pretrained denoisers ( |
00:27.771 |
0.0 |
Self-supervised learning from incomplete measurements of multiple operators. ( |
00:23.383 |
0.0 |
Use iterative reconstruction algorithms ( |
00:21.069 |
0.0 |
Reconstruct real CT sinograms with the 2DeteCT benchmark ( |
00:19.111 |
0.0 |
Learned Primal-Dual algorithm for CT scan. ( |
00:17.632 |
0.0 |
Distributed Training of Unfolded Networks ( |
00:16.442 |
0.0 |
Learned Iterative Soft-Thresholding Algorithm (LISTA) for compressed sensing ( |
00:15.213 |
0.0 |
In-vivo ultrafast ultrasound reconstruction with Plug-and-Play ( |
00:14.115 |
0.0 |
Training a reconstruction model ( |
00:14.074 |
0.0 |
Unfolded Chambolle-Pock for constrained image inpainting ( |
00:12.983 |
0.0 |
Using state-of-the-art diffusion models from HuggingFace Diffusers with DeepInverse ( |
00:10.587 |
0.0 |
Flow-Matching for posterior sampling and unconditional generation ( |
00:09.998 |
0.0 |
Low-field MRI denoising without ground truth ( |
00:09.531 |
0.0 |
Learned iterative custom prior ( |
00:08.847 |
0.0 |
Inference and fine-tune a foundation model ( |
00:08.583 |
0.0 |
Building your diffusion posterior sampling method using SDEs ( |
00:08.499 |
0.0 |
Self-supervised learning with measurement splitting ( |
00:08.187 |
0.0 |
Reconstruct accelerated non-Cartesian breast MRI acquisition data ( |
00:08.183 |
0.0 |
5 minute quickstart tutorial ( |
00:07.778 |
0.0 |
Distributed Plug-and-Play (PnP) Reconstruction ( |
00:07.358 |
0.0 |
Radio interferometric imaging with deepinverse ( |
00:07.332 |
0.0 |
Spatial unwrapping and modulo imaging ( |
00:07.285 |
0.0 |
Noisy data-fidelity terms for diffusion posterior sampling ( |
00:07.174 |
0.0 |
Distributed Physics Operators ( |
00:06.996 |
0.0 |
Implementing DiffPIR ( |
00:06.893 |
0.0 |
Distributed Denoiser with Image Tiling ( |
00:06.874 |
0.0 |
Self-supervised denoising with the UNSURE loss. ( |
00:06.659 |
0.0 |
Positron emission tomography (PET) in 3D ( |
00:06.268 |
0.0 |
Self-supervised learning with Equivariant Imaging for MRI. ( |
00:05.963 |
0.0 |
Imaging inverse problems with adversarial networks ( |
00:05.627 |
0.0 |
Using HuggingFace datasets ( |
00:05.556 |
0.0 |
2D PET reconstruction with the Brainweb dataset ( |
00:04.942 |
0.0 |
Multispectral demosaicing from raw sensor data ( |
00:04.898 |
0.0 |
Ultrasound despeckling from B-mode images ( |
00:04.835 |
0.0 |
Regularization by Denoising (RED) for Super-Resolution. ( |
00:04.817 |
0.0 |
Blind denoising with noise level estimation ( |
00:04.659 |
0.0 |
Low-dose CT with ASTRA backend and Total-Variation (TV) prior ( |
00:04.454 |
0.0 |
Image transformations for Equivariant Imaging ( |
00:03.966 |
0.0 |
Tour of MRI functionality in DeepInverse ( |
00:03.776 |
0.0 |
Image deblurring with Total-Variation (TV) prior ( |
00:03.719 |
0.0 |
Tour of forward sensing operators ( |
00:03.676 |
0.0 |
Uncertainty quantification with PnP-ULA. ( |
00:03.571 |
0.0 |
Single-pixel imaging with Spyrit ( |
00:03.517 |
0.0 |
Image reconstruction with a diffusion model ( |
00:03.442 |
0.0 |
Random phase retrieval and reconstruction methods. ( |
00:03.365 |
0.0 |
Image transforms for equivariance & augmentations ( |
00:03.287 |
0.0 |
DPIR method for PnP image deblurring. ( |
00:03.228 |
0.0 |
Patch priors for limited-angle computed tomography ( |
00:02.821 |
0.0 |
Positron emission tomography (PET) in 2D ( |
00:02.713 |
0.0 |
Super-resolution with SRResNet ( |
00:02.680 |
0.0 |
3D denoising of brain MRI with wavelet and TV priors ( |
00:02.596 |
0.0 |
Loading scientific images ( |
00:02.527 |
0.0 |
Blind Richardson-Lucy deconvolution ( |
00:02.511 |
0.0 |
Blind inverse problems with no reference metrics ( |
00:02.339 |
0.0 |
Expected Patch Log Likelihood (EPLL) for Denoising and Inpainting ( |
00:02.284 |
0.0 |
Bring your own dataset ( |
00:02.174 |
0.0 |
Self-supervised MRI reconstruction with Artifact2Artifact ( |
00:02.128 |
0.0 |
Tour of blur operators ( |
00:02.105 |
0.0 |
DPS – Posterior Sampling with Diffusion Models ( |
00:02.101 |
0.0 |
3D diffraction PSF ( |
00:01.945 |
0.0 |
Self-supervised denoising with the SURE loss. ( |
00:01.917 |
0.0 |
Self-supervised denoising with the Neighbor2Neighbor loss. ( |
00:01.847 |
0.0 |
Multi-scale Plug-and-Play for Inpainting ( |
00:01.639 |
0.0 |
Calibrating physics operators ( |
00:01.482 |
0.0 |
Poisson Inverse Problems with Maximum-Likelihood Expectation-Maximization (MLEM) ( |
00:01.437 |
0.0 |
Poisson denoising using Poisson2Sparse ( |
00:01.395 |
0.0 |
Remote sensing with satellite images ( |
00:01.324 |
0.0 |
Use a pretrained model ( |
00:01.123 |
0.0 |
Poisson-Gaussian Denoising with the Generalized Anscombe Transform ( |
00:01.078 |
0.0 |
Image deblurring with custom deep explicit prior. ( |
00:01.058 |
0.0 |
Image inpainting with wavelet prior ( |
00:01.007 |
0.0 |
Low-intensity STED fluorescence microscopy denoising ( |
00:00.906 |
0.0 |
Plug-and-Play algorithm with Mirror Descent for Poisson noise inverse problems. ( |
00:00.738 |
0.0 |
DEAL denoising and reconstruction ( |
00:00.704 |
0.0 |
Tour of ultrafast ultrasound in DeepInverse ( |
00:00.681 |
0.0 |
Vanilla PnP for computed tomography (CT). ( |
00:00.650 |
0.0 |
Self-supervised denoising with the Generalized R2R loss. ( |
00:00.646 |
0.0 |
Pattern Ordering in a Compressive Single Pixel Camera ( |
00:00.617 |
0.0 |
PnP with custom optimization algorithm (Primal-Dual Condat-Vu) ( |
00:00.609 |
0.0 |
Ptychography phase retrieval ( |
00:00.433 |
0.0 |
Spectral Methods for Non-Circular Deblurring with Liu-Jia Padding ( |
00:00.414 |
0.0 |
Building your custom MCMC sampling algorithm. ( |
00:00.328 |
0.0 |
Reconstructing an image using the deep image prior. ( |
00:00.290 |
0.0 |
Bring your own physics ( |
00:00.160 |
0.0 |
Single photon lidar operator for depth ranging. ( |
00:00.153 |
0.0 |