computer-vision-8

Image Reconstruction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in image-reconstruction-8

Trend

Dataset

Best Model

Actions

Edge-to-Shoes

Edge-to-Handbags

ImageNet 256x256

Libraries

i

Use these libraries to find image-reconstruction-8 models and implementations

wdika/mridc

5 papers 36

Datasets

CED

Subtasks

MRI Reconstruction

Most implemented papers

Unsupervised Monocular Depth Estimation with Left-Right Consistency

Oisin Mac Aodha, G. Brostow, Clément Godard•Mon Sep 12 2016

This paper proposes a novel training objective that enables the convolutional neural network to learn to perform single image depth estimation, despite the absence of ground truth depth data, and produces state of the art results for monocular depth estimation on the KITTI driving dataset.

3142

Content

ImageNet 256x256

Audio Set

Edge-to-Clothes

facebookresearch/fastMRI

4 papers 1,237

josiahwsmith10/thz-and-sub-thz-imag…

2 papers 10

CBCT Walnut

0

Paper Graph

Universal Style Transfer via Feature Transforms

Chen Fang, Xin Lu, Ming-Hsuan Yang, Zhaowen Wang, Jimei Yang, Yijun Li•Mon May 22 2017

The key ingredient of the method is a pair of feature transforms, whitening and coloring, that are embedded to an image reconstruction network that reflects a direct matching of feature covariance of the content image to a given style image.

1089 0

Paper Graph

Digging Into Self-Supervised Monocular Depth Estimation

Oisin Mac Aodha, G. Brostow, Clément Godard•Sun Jun 03 2018

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods. Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark.

2316 0

Paper Graph

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

F. Knoll, Jure Zbontar, Anuroop Sriram, Matthew Muckley, M. Bruno, Aaron Defazio, Marc Parente, Krzysztof J. Geras, Joe Katsnelson, H. Chandarana, Adriana Romero, Michael G. Rabbat, James Pinkerton, Duo Wang, N. Yakubova, Erich Owens, C. L. Zitnick, M. Recht, D. Sodickson, Y. Lui, M. Drozdzal, Pascal Vincent, Zizhao Zhang•Tue Nov 20 2018

The fastMRI dataset is introduced, a large-scale collection of both raw MR measurements and clinical MR images that can be used for training and evaluation of machine-learning approaches to MR image reconstruction.

982 0

Paper Graph

SwinIR: Image Restoration Using Swin Transformer

K. Zhang, L. Gool, Radu Timofte, Jingyun Liang, Guolei Sun, Jie Cao•Sun Aug 22 2021

A strong baseline model SwinIR is proposed for image restoration based on the Swin Transformer that outperforms state-of-the-art methods on different tasks by up to 0.14∼0.45dB, while the total number of parameters can be reduced byUp to 67%.

4127 0

Paper Graph

Assessment of data consistency through cascades of independently recurrent inference machines for fast and robust accelerated MRI reconstruction

D. Karkalousos, S. Noteboom, H. Hulst, F. Vos, M. Caan•Mon Nov 29 2021

The CIRIM showed highly promising generalization capabilities maintaining a very fair trade-off between reconstructed image quality and fast reconstruction times, which is crucial in the clinical workflow.

12 0

Paper Graph

Homotopic Gradients of Generative Density Priors for MR Image Reconstruction

Shanshan Wang, D. Liang, Cong Quan, Jinjie Zhou, Yuanzheng Zhu, Yang Chen, Qiegen Liu•Thu Aug 13 2020

This work trains a more powerful noise conditional score network by forming high-dimensional tensor as the network input at the training phase and estimates the target gradients in higher-dimensional space to tackle low-dimensional manifold and low data density region issues in generative density prior.

29 0

Paper Graph

Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks

Ming-Hsuan Yang, Wei-Sheng Lai, Jia-Bin Huang, N. Ahuja•Tue Oct 03 2017

This paper proposes the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution, and utilizes the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters.

862 0

Paper Graph

A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction

D. Rueckert, Jose Caballero, Jo Schlemper, J. Hajnal, A. Price•Tue Feb 28 2017

This work proposes a framework for reconstructing MR images from undersampled data using a deep cascade of convolutional neural networks to accelerate the data acquisition process and shows that for Cartesian undersampling of 2D cardiac MR images, the proposed method outperforms the state-of-the-art compressed sensing approaches.

364 0

Paper Graph

A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction

D. Rueckert, Jose Caballero, Jo Schlemper, J. Hajnal, A. Price•Fri Apr 07 2017

A framework for reconstructing dynamic sequences of 2-D cardiac magnetic resonance images from undersampled data using a deep cascade of convolutional neural networks (CNNs) to accelerate the data acquisition process is proposed and it is demonstrated that CNNs can learn spatio-temporal correlations efficiently by combining convolution and data sharing approaches.

1219 0

Paper Graph

Adding a benchmark result helps the community track progress.