scispace - formally typeset
Search or ask a question
Author

Jinli Suo

Bio: Jinli Suo is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Pixel. The author has an hindex of 28, co-authored 124 publications receiving 2587 citations. Previous affiliations of Jinli Suo include Chinese Academy of Sciences & MediaTech Institute.


Papers
More filters
Journal ArticleDOI
TL;DR: This model represents faces in each age group by a hierarchical And-or graph, in which And nodes decompose a face into parts to describe details crucial for age perception and Or nodes represent large diversity of faces by alternative selections.
Abstract: In this paper, we present a compositional and dynamic model for face aging. The compositional model represents faces in each age group by a hierarchical And-or graph, in which And nodes decompose a face into parts to describe details (e.g., hair, wrinkles, etc.) crucial for age perception and Or nodes represent large diversity of faces by alternative selections. Then a face instance is a transverse of the And-or graph-parse graph. Face aging is modeled as a Markov process on the parse graph representation. We learn the parameters of the dynamic model from a large annotated face data set and the stochasticity of face aging is modeled in the dynamics explicitly. Based on this model, we propose a face aging simulation and prediction algorithm. Inversely, an automatic age estimation algorithm is also developed under this representation. We study two criteria to evaluate the aging results using human perception experiments: (1) the accuracy of simulation: whether the aged faces are perceived of the intended age group, and (2) preservation of identity: whether the aged faces are perceived as the same person. Quantitative statistical analysis validates the performance of our aging model and age estimation algorithm.

306 citations

Journal ArticleDOI
TL;DR: A joint model is built to integrate the nonlocal self-similarity of video/hyperspectral frames and the rank minimization approach with the SCI sensing process and an alternating minimization algorithm is developed to solve the non-convex problem of SCI reconstruction.
Abstract: 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.

244 citations

Journal ArticleDOI
TL;DR: This paper proposes an iterative optimization framework incorporating phase retrieval and noise relaxation together, to realize FP reconstruction using low SNR images captured under short exposure time and could save ~ 80% exposure time to achieve similar retrieval accuracy compared to the conventional FP.
Abstract: Recently Fourier Ptychography (FP) has attracted great attention, due to its marked effectiveness in leveraging snapshot numbers for spatial resolution in large field-of-view imaging. To acquire high signal-to-noise-ratio (SNR) images under angularly varying illuminations for subsequent reconstruction, FP requires long exposure time, which largely limits its practical applications. In this paper, based on the recently reported Wirtinger flow algorithm, we propose an iterative optimization framework incorporating phase retrieval and noise relaxation together, to realize FP reconstruction using low SNR images captured under short exposure time. Experiments on both synthetic and real captured data validate the effectiveness of the proposed reconstruction method. Specifically, the proposed technique could save ~ 80% exposure time to achieve similar retrieval accuracy compared to the conventional FP. Besides, we have released our source code for non-commercial use.

153 citations

Journal ArticleDOI
TL;DR: This work proposes the use of a flat–curved–flat imaging strategy, in which the sample plane is magnified onto a large spherical image surface and then seamlessly conjugated to multiple planar sensors, to perform video-rate, gigapixel imaging of biological dynamics at centimetre scale and micrometre resolution.
Abstract: Large-scale imaging of biological dynamics with high spatiotemporal resolution is indispensable to system biology studies However, conventional microscopes have an inherent compromise between the achievable field of view and spatial resolution due to the space–bandwidth product theorem In addition, a further challenge is the ability to handle the enormous amount of data generated by a large-scale imaging platform Here, we break these bottlenecks by proposing the use of a flat–curved–flat imaging strategy, in which the sample plane is magnified onto a large spherical image surface and then seamlessly conjugated to multiple planar sensors Our real-time, ultra-large-scale, high-resolution (RUSH) imaging platform operates with a 10 × 12 mm2 field of view, a uniform resolution of ~120 μm after deconvolution and a data throughput of 51 gigapixels per second We use the RUSH platform to perform video-rate, gigapixel imaging of biological dynamics at centimetre scale and micrometre resolution, including brain-wide structural imaging and functional imaging in awake, behaving mice Video-rate imaging of the brains of awake mice with a field of view of 10 × 12 mm2 and a spatial resolution of 12 µm is accomplished

134 citations

Journal ArticleDOI
TL;DR: This work proposes to conduct multispectral imaging using a single bucket detector, to take full advantage of its high sensitivity, wide spectrum range, low cost, small size and light weight.
Abstract: Existing multispectral imagers mostly use available array sensors to separately measure 2D data slices in a 3D spatial-spectral data cube. Thus they suffer from low photon efficiency, limited spectrum range and high cost. To address these issues, we propose to conduct multispectral imaging using a single bucket detector, to take full advantage of its high sensitivity, wide spectrum range, low cost, small size and light weight. Technically, utilizing the detector’s fast response, a scene’s 3D spatial-spectral information is multiplexed into a dense 1D measurement sequence and then demultiplexed computationally under the single pixel imaging scheme. A proof-of-concept setup is built to capture multispectral data of 64 pixels × 64 pixels × 10 wavelength bands ranging from 450 nm to 650 nm, with the acquisition time being 1 minute. The imaging scheme holds great potentials for various low light and airborne applications and can be easily manufactured as production-volume portable multispectral imagers.

132 citations


Cited by
More filters
01 Jan 2004
TL;DR: Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance and describes numerous important application areas such as image based rendering and digital libraries.
Abstract: From the Publisher: The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

3,627 citations

19 Nov 2012

1,653 citations

Journal Article
TL;DR: In this article, the diffraction tomography theorem is adapted to one-dimensional length measurement and the resulting spectral interferometry technique is described and the first length measurements using this technique on a model eye and on a human eye in vivo are presented.
Abstract: The diffraction tomography theorem is adapted to one-dimensional length measurement. The resulting spectral interferometry technique is described and the first length measurements using this technique on a model eye and on a human eye in vivo are presented.

1,237 citations

Proceedings ArticleDOI
27 Feb 2017
TL;DR: In this article, a conditional adversarial autoencoder (CAAE) is proposed to learn a face manifold, traversing on which smooth age progression and regression can be realized simultaneously.
Abstract: If I provide you a face image of mine (without telling you the actual age when I took the picture) and a large amount of face images that I crawled (containing labeled faces of different ages but not necessarily paired), can you show me what I would look like when I am 80 or what I was like when I was 5? The answer is probably a No. Most existing face aging works attempt to learn the transformation between age groups and thus would require the paired samples as well as the labeled query image. In this paper, we look at the problem from a generative modeling perspective such that no paired samples is required. In addition, given an unlabeled image, the generative model can directly produce the image with desired age attribute. We propose a conditional adversarial autoencoder (CAAE) that learns a face manifold, traversing on which smooth age progression and regression can be realized simultaneously. In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator. The latent vector preserves personalized face features (i.e., personality) and the age condition controls progression vs. regression. Two adversarial networks are imposed on the encoder and generator, respectively, forcing to generate more photo-realistic faces. Experimental results demonstrate the appealing performance and flexibility of the proposed framework by comparing with the state-of-the-art and ground truth.

766 citations