arXiv subjects

Jiaming Liu

Publications and source records attributed to Jiaming Liu.

At least 199 records · Page 11Linked to original sources

arXiv2022

Online Deep Equilibrium Learning for Regularization by Denoising

Plug-and-Play Priors (PnP) and Regularization by Denoising (RED) are widely-used frameworks for solving imaging inverse problems by computing fixed-points of operators combining physical measurement models and learned image priors. While traditional PnP/RED formulations have focused on priors specified using image denoisers, there is a growing interest in learning PnP/RED priors that are end-to-end optimal. The recent Deep Equilibrium Models (DEQ) framework has enabled memory-efficient end-to-end learning of PnP/RED priors by implicitly differentiating through the fixed-point equations without storing intermediate activation values. However, the dependence of the computational/memory complexity of the measurement models in PnP/RED on the total number of measurements leaves DEQ impractical for many imaging applications. We propose ODER as a new strategy for improving the efficiency of DEQ through stochastic approximations of the measurement models. We theoretically analyze ODER giving insights into its convergence and ability to approximate the traditional DEQ approach. Our numerical results suggest the potential improvements in training/testing complexity due to ODER on three distinct imaging applications.

eess.IV↗

arXiv2022

Few-Shot Head Swapping in the Wild

The head swapping task aims at flawlessly placing a source head onto a target body, which is of great importance to various entertainment scenarios. While face swapping has drawn much attention, the task of head swapping has rarely been explored, particularly under the few-shot setting. It is inherently challenging due to its unique needs in head modeling and background blending. In this paper, we present the Head Swapper (HeSer), which achieves few-shot head swapping in the wild through two delicately designed modules. Firstly, a Head2Head Aligner is devised to holistically migrate pose and expression information from the target to the source head by examining multi-scale information. Secondly, to tackle the challenges of skin color variations and head-background mismatches in the swapping procedure, a Head2Scene Blender is introduced to simultaneously modify facial skin color and fill mismatched gaps in the background around the head. Particularly, seamless blending is achieved with the help of a Semantic-Guided Color Reference Creation procedure and a Blending UNet. Extensive experiments demonstrate that the proposed method produces superior head swapping results in a variety of scenes.

cs.CV↗

arXiv2022

Image Reconstruction for MRI using Deep CNN Priors Trained without Groundtruth

We propose a new plug-and-play priors (PnP) based MR image reconstruction method that systematically enforces data consistency while also exploiting deep-learning priors. Our prior is specified through a convolutional neural network (CNN) trained without any artifact-free ground truth to remove undersampling artifacts from MR images. The results on reconstructing free-breathing MRI data into ten respiratory phases show that the method can form high-quality 4D images from severely undersampled measurements corresponding to acquisitions of about 1 and 2 minutes in length. The results also highlight the competitive performance of the method compared to several popular alternatives, including the TGV regularization and traditional UNet3D.

eess.IV↗

arXiv2022

Monotonically Convergent Regularization by Denoising

Regularization by denoising (RED) is a widely-used framework for solving inverse problems by leveraging image denoisers as image priors. Recent work has reported the state-of-the-art performance of RED in a number of imaging applications using pre-trained deep neural nets as denoisers. Despite the recent progress, the stable convergence of RED algorithms remains an open problem. The existing RED theory only guarantees stability for convex data-fidelity terms and nonexpansive denoisers. This work addresses this issue by developing a new monotone RED (MRED) algorithm, whose convergence does not require nonexpansiveness of the deep denoising prior. Simulations on image deblurring and compressive sensing recovery from random matrices show the stability of MRED even when the traditional RED algorithm diverges.

eess.IV↗

arXiv2022

Learning-based Motion Artifact Removal Networks (LEARN) for Quantitative $R_2^\ast$ Mapping

Purpose: To introduce two novel learning-based motion artifact removal networks (LEARN) for the estimation of quantitative motion- and $B0$-inhomogeneity-corrected $R_2^\ast$ maps from motion-corrupted multi-Gradient-Recalled Echo (mGRE) MRI data. Methods: We train two convolutional neural networks (CNNs) to correct motion artifacts for high-quality estimation of quantitative $B0$-inhomogeneity-corrected $R_2^\ast$ maps from mGRE sequences. The first CNN, LEARN-IMG, performs motion correction on complex mGRE images, to enable the subsequent computation of high-quality motion-free quantitative $R_2^\ast$ (and any other mGRE-enabled) maps using the standard voxel-wise analysis or machine-learning-based analysis. The second CNN, LEARN-BIO, is trained to directly generate motion- and $B0$-inhomogeneity-corrected quantitative $R_2^\ast$ maps from motion-corrupted magnitude-only mGRE images by taking advantage of the biophysical model describing the mGRE signal decay. We show that both CNNs trained on synthetic MR images are capable of suppressing motion artifacts while preserving details in the predicted quantitative $R_2^\ast$ maps. Significant reduction of motion artifacts on experimental in vivo motion-corrupted data has also been achieved by using our trained models. Conclusion: Both LEARN-IMG and LEARN-BIO can enable the computation of high-quality motion- and $B0$-inhomogeneity-corrected $R_2^\ast$ maps. LEARN-IMG performs motion correction on mGRE images and relies on the subsequent analysis for the estimation of $R_2^\ast$ maps, while LEARN-BIO directly performs motion- and $B0$-inhomogeneity-corrected $R_2^\ast$ estimation. Both LEARN-IMG and LEARN-BIO jointly process all the available gradient echoes, which enables them to exploit spatial patterns available in the data. The high computational speed of LEARN-BIO is an advantage that can lead to a broader clinical application.

eess.IV↗

arXiv2021

Deformation-Compensated Learning for Image Reconstruction without Ground Truth

Deep neural networks for medical image reconstruction are traditionally trained using high-quality ground-truth images as training targets. Recent work on Noise2Noise (N2N) has shown the potential of using multiple noisy measurements of the same object as an alternative to having a ground-truth. However, existing N2N-based methods are not suitable for learning from the measurements of an object undergoing nonrigid deformation. This paper addresses this issue by proposing the deformation-compensated learning (DeCoLearn) method for training deep reconstruction networks by compensating for object deformations. A key component of DeCoLearn is a deep registration module, which is jointly trained with the deep reconstruction network without any ground-truth supervision. We validate DeCoLearn on both simulated and experimentally collected magnetic resonance imaging (MRI) data and show that it significantly improves imaging quality.

eess.IV↗

arXiv2021

SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-Resolution

With the development of Deep Neural Networks (DNNs), plenty of methods based on DNNs have been proposed for Single Image Super-Resolution (SISR). However, existing methods mostly train the DNNs on uniformly sampled LR-HR patch pairs, which makes them fail to fully exploit informative patches within the image. In this paper, we present a simple yet effective data augmentation method. We first devise a heuristic metric to evaluate the informative importance of each patch pair. In order to reduce the computational cost for all patch pairs, we further propose to optimize the calculation of our metric by integral image, achieving about two orders of magnitude speedup. The training patch pairs are sampled according to their informative importance with our method. Extensive experiments show our sampling augmentation can consistently improve the convergence and boost the performance of various SISR architectures, including EDSR, RCAN, RDN, SRCNN and ESPCN across different scaling factors (x2, x3, x4). Code is available at https://github.com/littlepure2333/SamplingAug

cs.CV↗

arXiv2021

Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition

The plug-and-play priors (PnP) and regularization by denoising (RED) methods have become widely used for solving inverse problems by leveraging pre-trained deep denoisers as image priors. While the empirical imaging performance and the theoretical convergence properties of these algorithms have been widely investigated, their recovery properties have not previously been theoretically analyzed. We address this gap by showing how to establish theoretical recovery guarantees for PnP/RED by assuming that the solution of these methods lies near the fixed-points of a deep neural network. We also present numerical results comparing the recovery performance of PnP/RED in compressive sensing against that of recent compressive sensing algorithms based on generative models. Our numerical results suggest that PnP with a pre-trained artifact removal network provides significantly better results compared to the existing state-of-the-art methods.

cs.CV↗

arXiv2021

Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation

Internet video delivery has undergone a tremendous explosion of growth over the past few years. However, the quality of video delivery system greatly depends on the Internet bandwidth. Deep Neural Networks (DNNs) are utilized to improve the quality of video delivery recently. These methods divide a video into chunks, and stream LR video chunks and corresponding content-aware models to the client. The client runs the inference of models to super-resolve the LR chunks. Consequently, a large number of models are streamed in order to deliver a video. In this paper, we first carefully study the relation between models of different chunks, then we tactfully design a joint training framework along with the Content-aware Feature Modulation (CaFM) layer to compress these models for neural video delivery. {\bf With our method, each video chunk only requires less than $1\% $ of original parameters to be streamed, achieving even better SR performance.} We conduct extensive experiments across various SR backbones, video time length, and scaling factors to demonstrate the advantages of our method. Besides, our method can be also viewed as a new approach of video coding. Our primary experiments achieve better video quality compared with the commercial H.264 and H.265 standard under the same storage cost, showing the great potential of the proposed method. Code is available at:\url{https://github.com/Neural-video-delivery/CaFM-Pytorch-ICCV2021}

eess.IV↗

arXiv2021

The old moving groups in the field of Taurus

In this work, we present a systematic search for stellar groups in the Taurus field by applying DBSCAN algorithm to the data from Gaia DR2. We find 22 groups, consisting of 8 young groups (Groups 1-8) at ages of 2-4Myr and distances of ~130-170pc, 14 old groups (Groups 9-22) at ages of 8-49Myr and distances of ~110-210pc. We characterize the disk properties of group members and find 19 new disk-bearing stars, 8 of which are in the young groups and 11 others belong to the comparatively old groups at ages of 8-11 Myr. We characterize the accretion properties of the group members with H$α$ emission line in their LAMOST spectra, and discover one source in Group 10 at an age of 10 Myr which still shows accretion activity. We investigate the kinematic relations among the old groups, and find that Group 9 is kinematically related to the known Taurus members and exclude any kinematic relations between Groups 10-22 and the known Taurus members.

astro-ph.SR↗

arXiv2021

CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems

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.

eess.IV↗

arXiv2021

SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees

Deep unfolding networks have recently gained popularity in the context of solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with the number of measurements, limiting their applicability to large-scale imaging inverse problems. We propose SGD-Net as a new methodology for improving the efficiency of deep unfolding through stochastic approximations of the data-consistency layers. Our theoretical analysis shows that SGD-Net can be trained to approximate batch deep unfolding networks to an arbitrary precision. Our numerical results on intensity diffraction tomography and sparse-view computed tomography show that SGD-Net can match the performance of the batch network at a fraction of training and testing complexity.

eess.IV↗

arXiv2020

Joint Reconstruction and Calibration using Regularization by Denoising

Regularization by denoising (RED) is a broadly applicable framework for solving inverse problems by using priors specified as denoisers. While RED has been shown to provide state-of-the-art performance in a number of applications, existing RED algorithms require exact knowledge of the measurement operator characterizing the imaging system, limiting their applicability in problems where the measurement operator has parametric uncertainties. We propose a new method, called Calibrated RED (Cal-RED), that enables joint calibration of the measurement operator along with reconstruction of the unknown image. Cal-RED extends the traditional RED methodology to imaging problems that require the calibration of the measurement operator. We validate Cal-RED on the problem of image reconstruction in computerized tomography (CT) under perturbed projection angles. Our results corroborate the effectiveness of Cal-RED for joint calibration and reconstruction using pre-trained deep denoisers as image priors.

eess.IV↗

arXiv2020

Practical Deep Raw Image Denoising on Mobile Devices

Deep learning-based image denoising approaches have been extensively studied in recent years, prevailing in many public benchmark datasets. However, the stat-of-the-art networks are computationally too expensive to be directly applied on mobile devices. In this work, we propose a light-weight, efficient neural network-based raw image denoiser that runs smoothly on mainstream mobile devices, and produces high quality denoising results. Our key insights are twofold: (1) by measuring and estimating sensor noise level, a smaller network trained on synthetic sensor-specific data can out-perform larger ones trained on general data; (2) the large noise level variation under different ISO settings can be removed by a novel k-Sigma Transform, allowing a small network to efficiently handle a wide range of noise levels. We conduct extensive experiments to demonstrate the efficiency and accuracy of our approach. Our proposed mobile-friendly denoising model runs at ~70 milliseconds per megapixel on Qualcomm Snapdragon 855 chipset, and it is the basis of the night shot feature of several flagship smartphones released in 2019.

eess.IV↗

arXiv2020

Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors

Regularization by denoising (RED) is a recently developed framework for solving inverse problems by integrating advanced denoisers as image priors. Recent work has shown its state-of-the-art performance when combined with pre-trained deep denoisers. However, current RED algorithms are inadequate for parallel processing on multicore systems. We address this issue by proposing a new asynchronous RED (ASYNC-RED) algorithm that enables asynchronous parallel processing of data, making it significantly faster than its serial counterparts for large-scale inverse problems. The computational complexity of ASYNC-RED is further reduced by using a random subset of measurements at every iteration. We present complete theoretical analysis of the algorithm by establishing its convergence under explicit assumptions on the data-fidelity and the denoiser. We validate ASYNC-RED on image recovery using pre-trained deep denoisers as priors.

eess.IV↗

arXiv2020

Deep Image Reconstruction using Unregistered Measurements without Groundtruth

One of the key limitations in conventional deep learning based image reconstruction is the need for registered pairs of training images containing a set of high-quality groundtruth images. This paper addresses this limitation by proposing a novel unsupervised deep registration-augmented reconstruction method (U-Dream) for training deep neural nets to reconstruct high-quality images by directly mapping pairs of unregistered and artifact-corrupted images. The ability of U-Dream to circumvent the need for accurately registered data makes it widely applicable to many biomedical image reconstruction tasks. We validate it in accelerated magnetic resonance imaging (MRI) by training an image reconstruction model directly on pairs of undersampled measurements from images that have undergone nonrigid deformations.

eess.IV↗

arXiv2020

Phase II of the LAMOST-Kepler/K2 survey. I. Time series of medium-resolution spectroscopic observations

Phase \RNum{2} of the LAMOST-{\sl Kepler/K}2 survey (LK-MRS), initiated in 2018, aims at collecting medium-resolution spectra ($R\sim7,500$; hereafter MRS) for more than $50,000$ stars with multiple visits ($\sim60$ epochs) over a period of 5 years (2018 September to 2023 June). We selected 20 footprints distributed across the {\sl Kepler} field and six {\sl K}2 campaigns, with each plate containing a number of stars ranging from $\sim2,000$ to $\sim 3,000$. During the first year of observations, the LK-MRS has already collected $\sim280,000$ and $\sim369,000$ high-quality spectra in the blue and red wavelength range, respectively. The atmospheric parameters and radial velocities for $\sim259,000$ spectra of $21,053$ targets were successfully calculated by the LASP pipeline. The internal uncertainties for the effective temperature, surface gravity, metallicity, and radial velocity are found to be $100$\,K, $0.15$\,dex, $0.09$\,dex, and $1.00$\,km\,s$^{-1}$, respectively. We found $14,997$, $20,091$, and $1,514$ stars in common with the targets from the LAMOST low-resolution survey (LRS), GAIA and APOGEE, respectively, corresponding to a fraction of $\sim70\%$, $\sim95\%$ and $\sim7.2\%$. In general, the parameters derived from LK-MRS spectra are consistent with those obtained from the LRS and APOGEE spectra, but the scatter increases as the surface gravity decreases when comparing with the measurements from APOGEE. A large discrepancy is found with the GAIA values of the effective temperature. The comparisons of radial velocities of LK-MRS to GAIA and LK-MRS to APOGEE nearly follow an Gaussian distribution with a mean $μ\sim1.10$ and $0.73$\,km\,s$^{-1}$, respectively.

astro-ph.SR↗

arXiv2020

SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors

Two features desired in a three-dimensional (3D) optical tomographic image reconstruction algorithm are the ability to reduce imaging artifacts and to do fast processing of large data volumes. Traditional iterative inversion algorithms are impractical in this context due to their heavy computational and memory requirements. We propose and experimentally validate a novel scalable iterative mini-batch algorithm (SIMBA) for fast and high-quality optical tomographic imaging. SIMBA enables high-quality imaging by combining two complementary information sources: the physics of the imaging system characterized by its forward model and the imaging prior characterized by a denoising deep neural net. SIMBA easily scales to very large 3D tomographic datasets by processing only a small subset of measurements at each iteration. We establish the theoretical fixed-point convergence of SIMBA under nonexpansive denoisers for convex data-fidelity terms. We validate SIMBA on both simulated and experimentally collected intensity diffraction tomography (IDT) datasets. Our results show that SIMBA can significantly reduce the computational burden of 3D image formation without sacrificing the imaging quality.

eess.IV↗