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.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Introduction to linear and nonlinear programming

50 Years of Image Analysis

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.

Measurement of intraocular distances by backscattering spectral interferometry

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.

/pdf/age-progression-regression-by-conditional-adversarial-4o0qnp7kc0.pdf

Age Progression/Regression by Conditional Adversarial Autoencoder

Non-uniform camera shake removal is a knotty problem which plagues the researchers due to the huge computational cost of high-dimensional blur kernel estimation. To address this problem, we propose an acceleration method to compute the 3D projection of 2D local blur kernels fast, and then derive the 3D kernel by interpolating from a minimal set of local blur kernels. Under this scheme, a perpendicular acquisition system is proposed to increase the projection variance for reducing the ill-posedness of 3D kernel estimation. Finally, based on the minimal 3D kernel solver, a RANSAC-based framework is developed to raise the robustness to estimation error of 2D local blur kernels. In experiments, we validate the effectiveness and efficiency of our approach on both synthetic and real captured data, and promising results are obtained.

/pdf/efficient-3d-kernel-estimation-for-non-uniform-camera-shake-4d8k4omx2g.pdf

Efficient 3D kernel estimation for non-uniform camera shake removal using perpendicular camera system

Computational imaging apparatus are modern systems that consist of generalized optics and image processing capability. The term ‘computational imaging’, also known as ‘computational photography’, describes the emerging field of optical systems in which an image is not formed by a lens and simply sampled onto the detector. Rather, the process of image formation is facilitated by both the power of the optical elements and the computational processing of the sampled light signal. Such an imaging system integrally incorporates optics, optoelectronics, and signal processing. These systems can be optimized to greatly increase the performance of the imaging apparatus that utilizing solely traditional optics. By introducing computation into spectral imaging, breakthroughs could be achieved in imaging speed, resolution and spectral accuracy.

Computational Hyperspectral Imaging

We review the recent deep learning reconstruction algorithms for spectral snapshot compressive imaging (SCI), which used a single shot measurement to capture the three-dimensional (3D, x, y, λ) spectral image. Recent years, deep learning has been the dominant algorithm to conduct reconstruction due to high speed and accuracy. Various frameworks such as end-to-end neural networks, deep unfolding, plug-and-play networks have been developed. Furthermore, the untrained neural networks have also been used. In this paper, we review diverse deep learning methods for spectral SCI. In addition to the aforementioned frameworks, different backbones and network structures including the most recent Transformers are reviewed. Simulation and real data results are presented to compare these methods.

Recent advances of deep learning for spectral snapshot compressive imaging

The neural radiance field (NeRF) constructs an implicit representation function to substitute the traditional 3D representation, such as point cloud, mesh, and voxels, leading to consistent and efficient image rendering at desired observing spatial position. However, NeRF requires dense sampling in 3D space to build the continuous representation function. The huge amount of sampling points occupies intensive computing resources, which hinders NeRF from being integrated into the lightweight system. In this paper, we present a learning-based sampling strategy, which conducts dense sampling in regions with rich texture and sparse sampling in other regions, extremely reducing the computation resources and accelerating the learning speed. Furthermore, to alleviate the additional computation overhead caused by the proposed sampling strategy, we present a distributed structure to conduct the sampling decision individually. The distributed design releases the computation burden on the devices, which enables the deployment of the proposed strategy to the practical systems.

Learning-based ray sampling strategy for computation efficient neural radiance field generation

Despite their remarkable performance, deep neural networks remain mostly ``black boxes'', suggesting inexplicability and hindering their wide applications in fields requiring making rational decisions. Here we introduce HOPE (High-order Polynomial Expansion), a method for expanding a network into a high-order Taylor polynomial on a reference input. Specifically, we derive the high-order derivative rule for composite functions and extend the rule to neural networks to obtain their high-order derivatives quickly and accurately. From these derivatives, we can then derive the Taylor polynomial of the neural network, which provides an explicit expression of the network's local interpretations. Numerical analysis confirms the high accuracy, low computational complexity, and good convergence of the proposed method. Moreover, we demonstrate HOPE's wide applications built on deep learning, including function discovery, fast inference, and feature selection. The code is available at https://github.com/HarryPotterXTX/HOPE.git.

Jinli Suo

Papers

Efficient 3D kernel estimation for non-uniform camera shake removal using perpendicular camera system

Computational Hyperspectral Imaging

Recent advances of deep learning for spectral snapshot compressive imaging

Learning-based ray sampling strategy for computation efficient neural radiance field generation

HOPE: High-order Polynomial Expansion of Black-box Neural Networks