Image reconstruction and synthesis have witnessed remarkable progress thanks to the development of generative models. Nonetheless, gaps could still exist between the real and generated images, especially in the frequency domain. In this study, we show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further. We propose a novel focal frequency loss, which allows a model to adaptively focus on frequency components that are hard to synthesize by down-weighting the easy ones. This objective function is complementary to existing spatial losses, offering great impedance against the loss of important frequency information due to the inherent bias of neural networks. We demonstrate the versatility and effectiveness of focal frequency loss to improve popular models, such as VAE, pix2pix, and SPADE, in both perceptual quality and quantitative performance. We further show its potential on StyleGAN2.
FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging
School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；Changzhi Medical College（长治医学院）；the Engineering Research Centre for Intelligent Data Assisted Diagnosis and Treatment in Shanxi Province（山西省智能数据辅助诊断与治疗工程研究中心）；Uniwave Artificial Intelligence Technology Co., Ltd.（Uniwave人工智能科技有限公司）
This paper describes a novel approach to partially reconstruct high-resolution 4D light fields from a stack of differently focused photographs taken with a fixed camera. First, a focus map is calculated from this stack using a simple approach combining gradient detection and region expansion with graph-cut. Then, this focus map is converted into a depth map thanks to the calibration of the camera. We proceed after this with the tomographic reconstruction of the epipolar images by back-projecting the focused regions of the scene only. We call it masked back-projection. The angles of back-projec…
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
The University of Hong Kong（香港大学）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Adelaide（阿德莱德大学）；SenseTime Research（商汤科技研究院）；Zhejiang University（浙江大学）
Duke University（杜克大学）；University of Arizona（亚利桑那大学）
We demonstrate a physics-aware transformer for feature-based data fusion from cameras with diverse resolution, color spaces, focal planes, focal lengths, and exposure. We also demonstrate a scalable solution for synthetic training data generation for the transformer using open-source computer graphics software. We demonstrate image synthesis on arrays with diverse spectral responses, instantaneous field of view and frame rate.
University of Florida（佛罗里达大学）；Georgia State University（佐治亚州立大学）
Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and synthesis of multi-modal MRI using incomplete k-space data of several source modalities as inputs. The output of our model includes reconstructed images of the source modalities and high-quality image synthesized in the target modality. Our proposed model is formulated as a variational problem that leverages several learnable modality-specific feature extract…
Division-of-focal-plane (DoFP) polarization imaging technical recently has been applied in many fields. However, the images captured by such sensors cannot be used directly because they suffer from instantaneous field-of-view errors and low resolution problem. This paper builds a fast DoFP demosaicing system with proposed progressive polarization demosaicing convolutional neural network (PPDN), which is specifically designed for edge-side GPU devices like Navidia Jetson TX2. The proposed network consists of two parts: reconstruction stage and refining stage. The former recovers four polarizati…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Rochester（罗切斯特大学）；University of Science and Technology of China（中国科学技术大学）
It is a long-standing challenge to reconstruct Cone Beam Computed Tomography (CBCT) of the lung under respiratory motion. This work takes a step further to address a challenging setting in reconstructing a multi-phase}4D lung image from just a single}3D CBCT acquisition. To this end, we introduce REpiratory-GAted Synthesis of views, or REGAS. REGAS proposes a self-supervised method to synthesize the undersampled tomographic views and mitigate aliasing artifacts in reconstructed images. This method allows a much better estimation of between-phase Deformation Vector Fields (DVFs), which are used…
Recently, a number of approaches to low-dose computed tomography (CT) have been developed and deployed in commercialized CT scanners. Tube current reduction is perhaps the most actively explored technology with advanced image reconstruction algorithms. Sparse data sampling is another viable option to the low-dose CT, and sparse-view CT has been particularly of interest among the researchers in CT community. Since analytic image reconstruction algorithms would lead to severe image artifacts, various iterative algorithms have been developed for reconstructing images from sparsely view-sampled pr…
University of Science and Technology of China（中国科学技术大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to …
A Unified Framework for Multimodal Image Reconstruction and Synthesis using Denoising Diffusion Models
Department of Computer Science and Engineering, Washington University in St. Louis（华盛顿大学圣路易斯分校计算机科学与工程系）；Mallinckrodt Institute of Radiology, Washington University in St. Louis（华盛顿大学圣路易斯分校马林克罗德特放射医学研究所）；Department of Electrical and Systems Engineering, Washington University in St. Louis（华盛顿大学圣路易斯分校电气与系统工程系）；Department of Neurology, Washington University in St. Louis（华盛顿大学圣路易斯分校神经病学系）；Department of Biomedical Engineering, Washington University in St. Louis（华盛顿大学圣路易斯分校生物医学工程系）；Division of Biology and Biomedical Sciences, Washington University in St. Louis（华盛顿大学圣路易斯分校生物学与生物医学科学 division）；Department of Electrical and Computer Engineering, University of Wisconsin–Madison（威斯康星大学麦迪逊分校电气与计算机工程系）
Convolutional Neural Networks (CNN) based image reconstruction methods have been intensely used for X-ray computed tomography (CT) reconstruction applications. Despite great success, good performance of this data-based approach critically relies on a representative big training data set and a dense convoluted deep network. The indiscriminating convolution connections over all dense layers could be prone to over-fitting, where sampling biases are wrongly integrated as features for the reconstruction. In this paper, we report a robust hierarchical synthesis reconstruction approach, where trainin…
This dissertation is devoted to provide advanced nonconvex nonsmooth variational models of (Magnetic Resonance Image) MRI reconstruction, efficient learnable image reconstruction algorithms and parameter training algorithms that improve the accuracy and robustness of the optimization-based deep learning methods for compressed sensing MRI reconstruction and synthesis. The first part introduces a novel optimization based deep neural network whose architecture is inspired by proximal gradient descent for solving a variational model. The second part is a substantial extension of the preliminary wo…
We examine 3D reconstruction of architectural scenes in unordered sets of uncalibrated images. We introduce a linear method to self-calibrate and find the metric reconstruction of a camera pair. We assume unknown and different focal lengths but otherwise known internal camera parameters and a known projective reconstruction of the camera pair. We recover two possible camera configurations in space and use the Cheirality condition, that all 3D scene points are in front of both cameras, to disambiguate the solution. We show in two Theorems, first that the two solutions are in mirror positions an…
Multi-contrast MRI acquisitions of an anatomy enrich the magnitude of information available for diagnosis. Yet, excessive scan times associated with additional contrasts may be a limiting factor. Two mainstream approaches for enhanced scan efficiency are reconstruction of undersampled acquisitions and synthesis of missing acquisitions. In reconstruction, performance decreases towards higher acceleration factors with diminished sampling density particularly at high-spatial-frequencies. In synthesis, the absence of data samples from the target contrast can lead to artefactual sensitivity or inse…
Deep learning-based models have been shown to improve the accuracy of fingerprint recognition. While these algorithms show exceptional performance, they require large-scale fingerprint datasets for training and evaluation. In this work, we propose a novel fingerprint synthesis and reconstruction framework based on the StyleGan2 architecture, to address the privacy issues related to the acquisition of such large-scale datasets. We also derive a computational approach to modify the attributes of the generated fingerprint while preserving their identity. This allows synthesizing multiple differen…
Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences（中国科学院上海光学精密机械研究所）；The University of Hong Kong（香港大学）
Light field reconstruction from images captured by focal plane sweeping can achieve high lateral resolution comparable to the modern camera sensor. This is impossible for the conventional micro-lenslet based light field capture systems. However, the severe defocus noise and the low depth resolution limit its applications. In this paper, we analyze the defocus noise and the depth resolution in the focal plane sweeping based light field reconstruction technique, and propose a method to reduce the defocus noise and improve the depth resolution. Both numerical and experimental results verify the p…
Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey
NTU（国立台湾大学）；Caltech（加州理工学院）；Westlake University（西湖大学）；UCSD（加州大学圣地亚哥分校）；University of Oxford（牛津大学）；Nanjing University（南京大学）；HKU（香港大学）；University of Cambridge（剑桥大学）；Hillbot；MPI for Informatics（信息研究所）；Harvard University（哈佛大学）；MIT（麻省理工学院）
The University of Tokyo（东京大学）；Microsoft Research Asia（微软亚洲研究院）
The Multiplane Image (MPI), containing a set of fronto-parallel RGBA layers, is an effective and efficient representation for view synthesis from sparse inputs. Yet, its fixed structure limits the performance, especially for surfaces imaged at oblique angles. We introduce the Structural MPI (S-MPI), where the plane structure approximates 3D scenes concisely. Conveying RGBA contexts with geometrically-faithful structures, the S-MPI directly bridges view synthesis and 3D reconstruction. It can not only overcome the critical limitations of MPI, i.e., discretization artifacts from sloped surfaces …
A self-supervised cyclic neural-analytic approach for novel view synthesis and 3D reconstruction
National University of Science and Technology "Politehnica" Bucharest（布加勒斯特理工国立大学）；"Simion Stoilow" Institute of Mathematics of the Romanian Academy（罗马尼亚科学院西米翁斯托伊洛夫数学研究所）；NORCE Norwegian Research Centre AS（NORCE挪威研究中心AS公司）
University of Amsterdam（阿姆斯特丹大学）；Shanghai Jiao Tong University（上海交通大学）
This paper strives to generate a synthetic computed tomography (CT) image from a magnetic resonance (MR) image. The synthetic CT image is valuable for radiotherapy planning when only an MR image is available. Recent approaches have made large strides in solving this challenging synthesis problem with convolutional neural networks that learn a mapping from MR inputs to CT outputs. In this paper, we find that all existing approaches share a common limitation: reconstruction breaks down in and around the high-frequency parts of CT images. To address this common limitation, we introduce frequency-…
ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors
School of AIA, Huazhong University of Science and Technology（华中科技大学人工智能学院）；the S-Lab, Nanyang Technological University (NTU)（南洋理工大学S实验室）；the Beijing Academy of Artificial Intelligence (BAAI)（北京人工智能研究院）；Zhejiang University (ZJU)（浙江大学）；the Institute for AI Industry Research (AIR), Tsinghua University (THU)（清华大学人工智能产业研究院）
Obtaining photorealistic reconstructions of objects from sparse views is inherently ambiguous and can only be achieved by learning suitable reconstruction priors. Earlier works on sparse rigid object reconstruction successfully learned such priors from large datasets such as CO3D. In this paper, we extend this approach to dynamic objects. We use cats and dogs as a representative example and introduce Common Pets in 3D (CoP3D), a collection of crowd-sourced videos showing around 4,200 distinct pets. CoP3D is one of the first large-scale datasets for benchmarking non-rigid 3D reconstruction "in …
Center for AI Technology (CAIT), Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所人工智能技术中心（CAIT））
We present a dataset of 1000 video sequences of human portraits recorded in real and uncontrolled conditions by using a handheld smartphone accompanied by an external high-quality depth camera. The collected dataset contains 200 people captured in different poses and locations and its main purpose is to bridge the gap between raw measurements obtained from a smartphone and downstream applications, such as state estimation, 3D reconstruction, view synthesis, etc. The sensors employed in data collection are the smartphone's camera and Inertial Measurement Unit (IMU), and an external Azure Kinect…
Neural Radiance Fields (NeRF) has achieved impressive results in single object scene reconstruction and novel view synthesis, which have been demonstrated on many single modality and single object focused indoor scene datasets like DTU, BMVS, and NeRF Synthetic.However, the study of NeRF on large-scale outdoor scene reconstruction is still limited, as there is no unified outdoor scene dataset for large-scale NeRF evaluation due to expensive data acquisition and calibration costs. In this paper, we propose a large-scale outdoor multi-modal dataset, OMMO dataset, containing complex land objects …
Peking University（北京大学）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Peng Cheng Laboratory（鹏城实验室）；City University of Hong Kong（香港城市大学）；Communication University of China（中国传媒大学）
Existing compression methods typically focus on the removal of signal-level redundancies, while the potential and versatility of decomposing visual data into compact conceptual components still lack further study. To this end, we propose a novel conceptual compression framework that encodes visual data into compact structure and texture representations, then decodes in a deep synthesis fashion, aiming to achieve better visual reconstruction quality, flexible content manipulation, and potential support for various vision tasks. In particular, we propose to compress images by a dual-layered mode…
Visual Prototype Conditioned Focal Region Generation for UAV-Based Object Detection
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
