arXiv subjects

Qionghai Dai

Publications and source records attributed to Qionghai Dai.

At least 55 records · Page 3Linked to original sources

arXiv2020

PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction

Modeling 3D humans accurately and robustly from a single image is very challenging, and the key for such an ill-posed problem is the 3D representation of the human models. To overcome the limitations of regular 3D representations, we propose Parametric Model-Conditioned Implicit Representation (PaMIR), which combines the parametric body model with the free-form deep implicit function. In our PaMIR-based reconstruction framework, a novel deep neural network is proposed to regularize the free-form deep implicit function using the semantic features of the parametric model, which improves the generalization ability under the scenarios of challenging poses and various clothing topologies. Moreover, a novel depth-ambiguity-aware training loss is further integrated to resolve depth ambiguities and enable successful surface detail reconstruction with imperfect body reference. Finally, we propose a body reference optimization method to improve the parametric model estimation accuracy and to enhance the consistency between the parametric model and the implicit function. With the PaMIR representation, our framework can be easily extended to multi-image input scenarios without the need of multi-camera calibration and pose synchronization. Experimental results demonstrate that our method achieves state-of-the-art performance for image-based 3D human reconstruction in the cases of challenging poses and clothing types.

cs.CV↗

arXiv2020

PoNA: Pose-guided Non-local Attention for Human Pose Transfer

Human pose transfer, which aims at transferring the appearance of a given person to a target pose, is very challenging and important in many applications. Previous work ignores the guidance of pose features or only uses local attention mechanism, leading to implausible and blurry results. We propose a new human pose transfer method using a generative adversarial network (GAN) with simplified cascaded blocks. In each block, we propose a pose-guided non-local attention (PoNA) mechanism with a long-range dependency scheme to select more important regions of image features to transfer. We also design pre-posed image-guided pose feature update and post-posed pose-guided image feature update to better utilize the pose and image features. Our network is simple, stable, and easy to train. Quantitative and qualitative results on Market-1501 and DeepFashion datasets show the efficacy and efficiency of our model. Compared with state-of-the-art methods, our model generates sharper and more realistic images with rich details, while having fewer parameters and faster speed. Furthermore, our generated images can help to alleviate data insufficiency for person re-identification.

cs.CV↗

arXiv2020

Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit

Application-specific optical processors have been considered disruptive technologies for modern computing that can fundamentally accelerate the development of artificial intelligence (AI) by offering substantially improved computing performance. Recent advancements in optical neural network architectures for neural information processing have been applied to perform various machine learning tasks. However, the existing architectures have limited complexity and performance; and each of them requires its own dedicated design that cannot be reconfigured to switch between different neural network models for different applications after deployment. Here, we propose an optoelectronic reconfigurable computing paradigm by constructing a diffractive processing unit (DPU) that can efficiently support different neural networks and achieve a high model complexity with millions of neurons. It allocates almost all of its computational operations optically and achieves extremely high speed of data modulation and large-scale network parameter updating by dynamically programming optical modulators and photodetectors. We demonstrated the reconfiguration of the DPU to implement various diffractive feedforward and recurrent neural networks and developed a novel adaptive training approach to circumvent the system imperfections. We applied the trained networks for high-speed classifying of handwritten digit images and human action videos over benchmark datasets, and the experimental results revealed a comparable classification accuracy to the electronic computing approaches. Furthermore, our prototype system built with off-the-shelf optoelectronic components surpasses the performance of state-of-the-art graphics processing units (GPUs) by several times on computing speed and more than an order of magnitude on system energy efficiency.

eess.IV↗

arXiv2020

Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging

Snapshot compressive imaging (SCI) aims to capture the high-dimensional (usually 3D) images using a 2D sensor (detector) in a single snapshot. Though enjoying the advantages of low-bandwidth, low-power and low-cost, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging. The bottleneck lies in the reconstruction algorithms; they are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the widely used PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload and prove the convergence of PnP-GAP under the SCI hardware constraints. By employing deep denoising priors, we first time show that PnP can recover a UHD color video ($3840\times 1644\times 48$ with PNSR above 30dB) from a snapshot 2D measurement. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. The code is available at https://github.com/liuyang12/PnP-SCI.

eess.IV↗

arXiv2020

SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-view Stereopsis

Multi-view stereopsis (MVS) tries to recover the 3D model from 2D images. As the observations become sparser, the significant 3D information loss makes the MVS problem more challenging. Instead of only focusing on densely sampled conditions, we investigate sparse-MVS with large baseline angles since the sparser sensation is more practical and more cost-efficient. By investigating various observation sparsities, we show that the classical depth-fusion pipeline becomes powerless for the case with a larger baseline angle that worsens the photo-consistency check. As another line of the solution, we present SurfaceNet+, a volumetric method to handle the 'incompleteness' and the 'inaccuracy' problems induced by a very sparse MVS setup. Specifically, the former problem is handled by a novel volume-wise view selection approach. It owns superiority in selecting valid views while discarding invalid occluded views by considering the geometric prior. Furthermore, the latter problem is handled via a multi-scale strategy that consequently refines the recovered geometry around the region with the repeating pattern. The experiments demonstrate the tremendous performance gap between SurfaceNet+ and state-of-the-art methods in terms of precision and recall. Under the extreme sparse-MVS settings in two datasets, where existing methods can only return very few points, SurfaceNet+ still works as well as in the dense MVS setting. The benchmark and the implementation are publicly available at https://github.com/mjiUST/SurfaceNet-plus.

cs.CV↗

arXiv2020

Single-pixel coherent diffraction imaging

Complex-field imaging is indispensable for numerous applications at wavelengths from X-ray to THz, with amplitude describing transmittance (or reflectivity) and phase revealing intrinsic structure of the target object. Coherent diffraction imaging (CDI) employs iterative phase retrieval algorithms to process diffraction measurements and is the predominant non-interferometric method to image complex fields. However, the working spectrum of CDI is quite narrow, because the diffraction measurements on which it relies require dense array detection with ultra-high dynamic range. Here we report a single-pixel CDI technique that works for a wide waveband. A single-pixel detector instead of an array sensor is employed in the far field for detection. It repeatedly records the DC-only component of the diffracted wavefront scattered from an object as it is illuminated by a sequence of binary modulation patterns. This decreases the measurements' dynamic range by several orders of magnitude. We employ an efficient single-pixel phase-retrieval algorithm to jointly recover the object's 2D amplitude and phase maps from the 1D intensity-only measurements. No a priori object information is needed in the recovery process. We validate the technique's quantitative phase imaging nature using both calibrated phase objects and biological samples, and demonstrate its wide working spectrum with both 488-nm visible light and 980-nm near-infrared light. Our approach paves the way for complex-field imaging in a wider waveband where 2D detector arrays are not available, with broad applications in life and material sciences.

eess.IV↗

arXiv2020

PANDA: A Gigapixel-level Human-centric Video Dataset

We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset, for large-scale, long-term, and multi-object visual analysis. The videos in PANDA were captured by a gigapixel camera and cover real-world scenes with both wide field-of-view (~1 square kilometer area) and high-resolution details (~gigapixel-level/frame). The scenes may contain 4k head counts with over 100x scale variation. PANDA provides enriched and hierarchical ground-truth annotations, including 15,974.6k bounding boxes, 111.8k fine-grained attribute labels, 12.7k trajectories, 2.2k groups and 2.9k interactions. We benchmark the human detection and tracking tasks. Due to the vast variance of pedestrian pose, scale, occlusion and trajectory, existing approaches are challenged by both accuracy and efficiency. Given the uniqueness of PANDA with both wide FoV and high resolution, a new task of interaction-aware group detection is introduced. We design a 'global-to-local zoom-in' framework, where global trajectories and local interactions are simultaneously encoded, yielding promising results. We believe PANDA will contribute to the community of artificial intelligence and praxeology by understanding human behaviors and interactions in large-scale real-world scenes. PANDA Website: http://www.panda-dataset.com.

cs.CV↗

arXiv2019

Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition

Image recognition is an important topic in computer vision and image processing, and has been mainly addressed by supervised deep learning methods, which need a large set of labeled images to achieve promising performance. However, in most cases, labeled data are expensive or even impossible to obtain, while unlabeled data are readily available from numerous free on-line resources and have been exploited to improve the performance of deep neural networks. To better exploit the power of unlabeled data for image recognition, in this paper, we propose a semi-supervised and generative approach, namely the semi-supervised self-growing generative adversarial network (SGGAN). Label inference is a key step for the success of semi-supervised learning approaches. There are two main problems in label inference: how to measure the confidence of the unlabeled data and how to generalize the classifier. We address these two problems via the generative framework and a novel convolution-block-transformation technique, respectively. To stabilize and speed up the training process of SGGAN, we employ the metric Maximum Mean Discrepancy as the feature matching objective function and achieve larger gain than the standard semi-supervised GANs (SSGANs), narrowing the gap to the supervised methods. Experiments on several benchmark datasets show the effectiveness of the proposed SGGAN on image recognition and facial attribute recognition tasks. By using the training data with only 4% labeled facial attributes, the SGGAN approach can achieve comparable accuracy with leading supervised deep learning methods with all labeled facial attributes.

cs.CV↗

arXiv2019

Super-resolution Imaging of the Fluorescent Dipole Assembly with Polarized Structured Illumination Microscopy

Fluorescence polarization microscopy images both the intensity and orientation of fluorescent dipoles, which plays a vital role in studying the molecular structure and dynamics of bio-complex. However, it is difficult to resolve the dipole assemblies on the subcellular structure and their dynamics in living cells with super-resolution. Here we report polarized structured illumination microscopy (pSIM), which decouples the entangled spatial and angular structured illumination through interpreting the dipoles in spatio-angular hyperspace. We demonstrate its application on a series of biological filamentous systems such as cytoskeleton networks and lambda-DNA, and report the dynamics of short actin sliding through myosin-coated surface. Further, pSIM reveals "side-by-side" organization of the actin ring structure in the membrane-associated periodic skeleton in hippocampal neurons. It also images the dipole dynamics of green fluorescent proteins labeled to the microtubules in live U2OS cells. pSIM can be applied directly to a large variety of commercial or home-built SIM systems.

physics.optics↗

arXiv2019

DeepHuman: 3D Human Reconstruction from a Single Image

We propose DeepHuman, an image-guided volume-to-volume translation CNN for 3D human reconstruction from a single RGB image. To reduce the ambiguities associated with the surface geometry reconstruction, even for the reconstruction of invisible areas, we propose and leverage a dense semantic representation generated from SMPL model as an additional input. One key feature of our network is that it fuses different scales of image features into the 3D space through volumetric feature transformation, which helps to recover accurate surface geometry. The visible surface details are further refined through a normal refinement network, which can be concatenated with the volume generation network using our proposed volumetric normal projection layer. We also contribute THuman, a 3D real-world human model dataset containing about 7000 models. The network is trained using training data generated from the dataset. Overall, due to the specific design of our network and the diversity in our dataset, our method enables 3D human model estimation given only a single image and outperforms state-of-the-art approaches.

cs.CV↗

arXiv2019

SimulCap : Single-View Human Performance Capture with Cloth Simulation

This paper proposes a new method for live free-viewpoint human performance capture with dynamic details (e.g., cloth wrinkles) using a single RGBD camera. Our main contributions are: (i) a multi-layer representation of garments and body, and (ii) a physics-based performance capture procedure. We first digitize the performer using multi-layer surface representation, which includes the undressed body surface and separate clothing meshes. For performance capture, we perform skeleton tracking, cloth simulation, and iterative depth fitting sequentially for the incoming frame. By incorporating cloth simulation into the performance capture pipeline, we can simulate plausible cloth dynamics and cloth-body interactions even in the occluded regions, which was not possible in previous capture methods. Moreover, by formulating depth fitting as a physical process, our system produces cloth tracking results consistent with the depth observation while still maintaining physical constraints. Results and evaluations show the effectiveness of our method. Our method also enables new types of applications such as cloth retargeting, free-viewpoint video rendering and animations.

cs.CV↗

arXiv2018

Capture Dense: Markerless Motion Capture Meets Dense Pose Estimation

We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture can help the collection of a high-quality dataset for training the dense pose detector. Specifically, we first introduce a novel markerless motion capture method that can take advantage of dense parsing capability provided by the dense pose detector. Thanks to the introduced dense human parsing ability, our method is demonstrated much more efficient, and accurate compared with the available state-of-the-art markerless motion capture approach. Second, we improve the performance of available dense pose detector by using multiview markerless motion capture data. Such dataset is beneficial to dense pose training because they are more dense and accurate and consistent, and can compensate for the corner cases such as unusual viewpoints. We quantitatively demonstrate the improved performance of our dense pose detector over the available DensePose. Our dense pose dataset and detector will be made public.

cs.CV↗

arXiv2018

High fidelity single-pixel imaging

Single-pixel imaging (SPI) is an emerging technique which has attracts wide attention in various research fields. However, restricted by the low reconstruction quality and large amount of measurements, the practical application is still in its infancy. Inspired by the fact that natural scenes exhibit unique degenerate structures in the low dimensional subspace, we propose to take advantage of the local prior in convolutional sparse coding to implement high fidelity single-pixel imaging. Specifically, by statistically learning strategy, the target scene can be sparse represented on an overcomplete dictionary. The dictionary is composed of various basis learned from a natural image database. We introduce the above local prior into conventional SPI framework to promote the final reconstruction quality. Experiments both on synthetic data and real captured data demonstrate that our method can achieve better reconstruction from the same measurements, and thus consequently reduce the number of required measurements for same reconstruction quality.

eess.IV↗

arXiv2018

Snapshot hyperspectral imaging via spectral basis multiplexing in Fourier domain

Hyperspectral imaging is an important tool having been applied in various fields, but still limited in observation of dynamic scenes. In this paper, we propose a snapshot hyperspectral imaging technique which exploits both spectral and spatial sparsity of natural scenes. Under the computational imaging scheme, we conduct spectral dimension reduction and spatial frequency truncation to the hyperspectral data cube and snapshot it in a low cost manner. Specifically, we modulate the spectral variations by several broadband spectral filters, and then map these modulated images into different regions in the Fourier domain. The encoded image compressed in both spectral and spatial are finally collected by a monochrome detector. Correspondingly, the reconstruction is essentially a Fourier domain extraction and spectral dimensional back projection with low computational load. This Fourier-spectral multiplexing in a 2D sensor simplifies both the encoding and decoding process, and makes hyperspectral data captured in a low cost manner. We demonstrate the high performance of our method by quantitative evaluation on simulation data and build a prototype system experimentally for further validation.

physics.ins-det↗

arXiv2018

Rank Minimization for Snapshot Compressive Imaging

Snapshot compressive imaging (SCI) refers to compressive imaging systems where multiple frames are mapped into a single measurement, with video compressive imaging and hyperspectral compressive imaging as two representative applications. Though exciting results of high-speed videos and hyperspectral images have been demonstrated, the poor reconstruction quality precludes SCI from wide applications.This paper aims to boost the reconstruction quality of SCI via exploiting the high-dimensional structure in the desired signal. We build a joint model to integrate the nonlocal self-similarity of video/hyperspectral frames and the rank minimization approach with the SCI sensing process. Following this, an alternating minimization algorithm is developed to solve this non-convex problem. We further investigate the special structure of the sampling process in SCI to tackle the computational workload and memory issues in SCI reconstruction. Both simulation and real data (captured by four different SCI cameras) results demonstrate that our proposed algorithm leads to significant improvements compared with current state-of-the-art algorithms. We hope our results will encourage the researchers and engineers to pursue further in compressive imaging for real applications.

cs.CV↗

arXiv2018

Fast 3D cell tracking with wide-field fluorescence microscopy through deep learning

Tracking cells in 3D at high speed continues to attract extensive attention for many biomedical applications, such as monitoring immune cell migration and observing tumor metastasis in flowing blood vessels. Here, we propose a deep convolutional neural networks (CNNs) based method to retrieve the 3D locations of the fluorophores from a single 2D image captured by a conventional wide-field fluorescence microscope without any hardware modification. The reported method converts the challenging 3D localization from an ill-posed model-based fitting problem, especially with dense samples and low signal-to-noise ratio, to a solvable multi-label classification problem through two cascaded CNNs, where deep learning technique has a great advantage over other algorithms. Compared with traditional kernel-fitting methods, the proposed method achieves more accurate and robust localization of multiple objects across a much larger axial range, which is validated by both simulation and experimental results on 3D distributed fluorescent beads. Moreover, in vivo 3D tracking of multiple blood cells in zebrafish at 100 fps further verifies the feasibility of our framework.

physics.optics↗

arXiv2018

DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor

We propose DoubleFusion, a new real-time system that combines volumetric dynamic reconstruction with data-driven template fitting to simultaneously reconstruct detailed geometry, non-rigid motion and the inner human body shape from a single depth camera. One of the key contributions of this method is a double layer representation consisting of a complete parametric body shape inside, and a gradually fused outer surface layer. A pre-defined node graph on the body surface parameterizes the non-rigid deformations near the body, and a free-form dynamically changing graph parameterizes the outer surface layer far from the body, which allows more general reconstruction. We further propose a joint motion tracking method based on the double layer representation to enable robust and fast motion tracking performance. Moreover, the inner body shape is optimized online and forced to fit inside the outer surface layer. Overall, our method enables increasingly denoised, detailed and complete surface reconstructions, fast motion tracking performance and plausible inner body shape reconstruction in real-time. In particular, experiments show improved fast motion tracking and loop closure performance on more challenging scenarios.

cs.CV↗

arXiv2018

Single-shot thermal ghost imaging using wavelength-division multiplexing

Ghost imaging (GI) is a potential imaging technique that reconstructs the target scene from its correlated measurements with a sequential of patterns. Restricted by the multi-shot principle, GI usually requires long acquisition time and is limited in observation of dynamic scenes. To handle this problem, this paper proposes a single-shot thermal ghost imaging scheme via wavelength-division multiplexing technique. Specifically, we generate thousands of patterns simultaneously by modulating a broadband light source with a wavelength dependent diffuser. These patterns carry the scene's spatial information and then the correlated measurements are coupled into a spectrometer for the final reconstruction. This technique accelerates the ghost imaging speed significantly and promotes the applications in dynamic ghost imaging.

physics.optics↗