David Kriegman

David Kriegman
University of California, San Diego | UCSD · Department of Computer Science and Engineering (CSE)

About

242
Publications
54,320
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
44,916
Citations
Citations since 2016
11 Research Items
13527 Citations
201620172018201920202021202205001,0001,5002,000
201620172018201920202021202205001,0001,5002,000
201620172018201920202021202205001,0001,5002,000
201620172018201920202021202205001,0001,5002,000

Publications

Publications (242)
Article
Full-text available
Up to 90% of global coral reefs are predicted to be severely degraded by 2050 under “business-as-usual” scenarios. To meet the scale and scope of this challenge, we propose designing and demonstrating a multi-modal system that can incorporate data from remote sensing (satellites, aircraft, and aerial drones), acoustics, genetics, sensor arrays, and...
Article
Full-text available
We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This is achieved by adding extra networks and losses that help regularize the features extracted by the backbone en...
Article
Full-text available
Massive coral bleaching events associated with high sea surface temperatures are forecast to become more frequent and severe in the future due to climate change. Monitoring colony recovery from bleaching disturbances over multiyear time frames is important for improving predictions of future coral community changes. However, there are currently few...
Article
Photometric stereo is widely used for 3D reconstruction. However, its use in scattering media such as water, biological tissue and fog has been limited until now, because of forward scattered light from both the source and object, as well as light scattered back from the medium (backscatter). Here we make three contributions to address the key mode...
Conference Paper
In this work, we present a novel 3D-Convolutional Neural Network (CNN) architecture called I2I-3D that predicts boundary location in volumetric data. Our fine-to-fine, deeply supervised framework addresses three critical issues to 3D boundary detection: (1) efficient, holistic, end-to-end volumetric label training and prediction (2) precise voxel-l...
Article
Full-text available
Large-scale imaging techniques are used increasingly for ecological surveys. However, manual analysis can be prohibitively expensive, creating a bottleneck between collected images and desired data-products. This bottleneck is particularly severe for benthic surveys, where millions of images are obtained each year. Recent automated annotation metho...
Conference Paper
Computational simulations provide detailed hemodynamics and physiological data that can assist in clinical decision-making. However, accurate cardiovascular simulations require complete 3D models constructed from image data. Though edge localization is a key aspect in pinpointing vessel walls in many segmentation tools, the edge detection algorithm...
Article
This paper presents our work on "SNaCK," a low-dimensional concept embedding algorithm that combines human expertise with automatic machine similarity kernels. Both parts are complimentary: human insight can capture relationships that are not apparent from the object's visual similarity and the machine can help relieve the human from having to exha...
Article
Full-text available
Size and growth rates for individual colonies are some of the most essential descriptive parameters for understanding coral communities, which are currently experiencing worldwide declines in health and extent. Accurately measuring coral colony size and changes over multiple years can reveal demographic, growth, or mortality patterns often not appa...
Article
Full-text available
Global climate change and other anthropogenic stressors have heightened the need to rapidly characterize ecological changes in marine benthic communities across large scales. Digital photography enables rapid collection of survey images to meet this need, but the subsequent image annotation is typically a time consuming, manual task. We investigate...
Article
Full-text available
Coral reefs globally are declining rapidly because of both local and global stressors. Improved monitoring tools are urgently needed to understand the changes that are occurring at appropriate temporal and spatial scales. Coral fluorescence imaging tools have the potential to improve both ecological and physiological assessments. Although fluoresce...
Conference Paper
As humans, we love to rank things. Top ten lists exist for everything from movie stars to scary animals. Ambiguities (i.e., ties) naturally occur in the process of ranking when people feel they cannot distinguish two items. Human reported rankings derived from star ratings abound on recommendation websites such as Yelp and Netflix. However, those w...
Article
Full-text available
To evaluate three new pixelwise rates of retinal height changes (PixR) strategies to reduce false positive errors while detecting glaucomatous progression. Diagnostic accuracy of nonparametric PixR-NP cluster test (CT), PixR-NP single threshold test (STT) and parametric PixR-P STT were compared to statistic image mapping (SIM) using Heidelberg Reti...
Article
Cost-sensitive multiclass classification has recently acquired significance in several appli-cations, through the introduction of multi- class datasets with well-defined misclassification costs. The design of classification algorithms for this setting is considered. It is argued that the unreliable performance of current algorithms is due to the in...
Article
We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a nonparametric set of global models for the part locations based on over 1,000 hand-labeled exemplar images. By assuming that the global models generate the part locations as hidden variables, we derive a Bayesian obje...
Conference Paper
We present a method for estimating the distance between a camera and a human head in 2D images from a calibrated camera. Leading head pose estimation algorithms focus mainly on head orientation (yaw, pitch, and roll) and translations perpendicular to the camera principal axis. Our contribution is a system that can estimate head pose under large tra...
Conference Paper
Successful face verification and recognition require matching corresponding points in a pair of images, and it is commonly acknowledged that alignment is a critical step prior to matching. Once aligned, a portion of the image can be compared or features can be extracted. This portion of the image, which we will call the face box, is often just the...
Conference Paper
Local descriptor methods are widely used in computer vision to compare local regions of images. These descriptors are often extracted relative to an estimated scale and rotation to provide invariance up to similarity transformations. The estimation of rotation and scale in local neighborhoods (also known as steering) is an imperfect process, howeve...
Conference Paper
The terms Biker, Punk, Hipster, Goth or Surfer often spark visual depictions of individuals with very distinct fashion styles. These visually salient styles can provide insight into the social identity of an individual. However, despite its potential usefulness, little work has been done to automatically classify images of people into social catego...
Conference Paper
Beyond day glow highlighters and psychedelic black light posters, it has been estimated that fluorescence is a property exhibited by 20% of objects. When a fluorescent material is illuminated with a short wavelength light, it re-emits light at a longer wavelength isotropically in a similar manner as a Lambertian surface reflects light. This hithert...
Conference Paper
The explosive growth in image sharing via social networks has produced exciting opportunities for the computer vision community in areas including face, text, product and scene recognition. In this work we turn our attention to group photos of people and ask the question: what can we determine about the social subculture or urban tribe to which the...
Conference Paper
Full-text available
With the proliferation of digital cameras and automatic acquisition systems, scientists can acquire vast numbers of images for quantitative analysis. However, much image analysis is conducted manually, which is both time consuming and prone to error. As a result, valuable scientific data from many domains sit dormant in image libraries awaiting ann...
Article
Full-text available
To detect localized glaucomatous structural changes using proper orthogonal decomposition (POD) framework with false-positive control that minimizes confirmatory follow-ups, and to compare the results to topographic change analysis (TCA). We included 167 participants (246 eyes) with ≥4 Heidelberg Retina Tomograph (HRT)-II exams from the Diagnostic...
Article
Keypoint matching between pairs of images using popular descriptors like SIFT or a faster variant called SURF is at the heart of many computer vision algorithms including recognition, mosaicing, and structure from motion. However, SIFT and SURF do not perform well for real-time or mobile applications. As an alternative very fast binary descriptors...
Conference Paper
Keypoint matching between pairs of images using popular descriptors like SIFT or a faster variant called SURF is at the heart of many computer vision algorithms including recognition, mosaicing, and structure from motion. However, SIFT and SURF do not perform well for real-time or mobile applications. As an alternative very fast binary descriptors...
Conference Paper
Full-text available
Face recognition approaches have traditionally focused on direct comparisons between aligned images, e.g. using pixel values or local image features. Such comparisons be- come prohibitively difficult when comparing faces across extreme differences in pose, illumination and expression. The goal of this work is to develop a face-similarity measure th...
Article
Full-text available
The interest in face recognition is moving toward real-world applications and uncontrolled sensing environments. An important application of interest is automated surveillance, where the objective is to recognize and track people who are on a watchlist. ...
Article
Full-text available
Many fingers wrinkle or shrivel when immersed in wa-ter. When used for biometric identification, the recognition rate for wrinkled fingers degrades. The impact of wrin-kling has so far not been well-understood. In this study, we present an investigation of how the finger-skin expan-sion due to wrinkling impacts the quality of scanned finger-prints...
Article
Full-text available
Face recognition systems classically recognize people individually. When presented with a group photograph containing multiple people, such systems implicitly assume statistical independence between each detected face. We question this basic assumption and consider instead that there is a dependence between face regions from the same image; after a...
Conference Paper
We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a non-parametric set of global models for the part locations based on over one thousand hand-labeled exemplar images. By assuming that the global models generate the part locations as hidden variables, we derive a Bayes...
Article
Full-text available
We present practical algorithms for stratified autocalibration with theoretical guarantees of global optimality. Given a projective reconstruction, we first upgrade it to affine by estimating the position of the plane at infinity. The plane at infinity is computed by globally minimizing a least squares formulation of the modulus constraints. In the...
Article
Full-text available
We describe a framework for improving the quality of personal photos by using a person's favorite photographs as examples. We observe that the majority of a person's photographs include the faces of a photographer's family and friends and often the errors in these photographs are the most disconcerting. We focus on correcting these types of images...
Conference Paper
Full-text available
We present a fast and robust system for estimating structure and motion using a stereo pair, with straight lines as features. Our first set of contributions are efficient algorithms to perform this estimation using a few (two or three) lines, which are well-suited for use in a hypothesize-and-test framework. Our second contribution is the design of...
Article
Full-text available
We design and implement a comprehensive study of the perception of gloss. This is the largest study of its kind to date, and the first to use real material measurements. In addition, we develop a novel multi-dimensional scaling (MDS) algorithm for analyzing pairwise comparisons. The data from the psychophysics study and the MDS algorithm is used to...
Conference Paper
Image blur and noise are difficult to avoid in many situations and can often ruin a photograph. We present a novel image deconvolution algorithm that deblurs and denoises an image given a known shift-invariant blur kernel. Our algorithm uses local color statistics derived from the image as a constraint in a unified framework that can be used for de...
Conference Paper
We present a practical algorithm that provably achieves the global optimum for a class of bilinear programs com- monly arising in computer vision applications. Our ap- proach relies on constructing tight convex relaxations of the objective function and minimizing it in a branch and bound framework. A key contribution of the paper is a novel, prov-...
Conference Paper
Image blur is caused by a number of factors such as motion, defocus, capturing light over the non-zero area of the aperture and pixel, the presence of anti-aliasing filters on a camera sensor, and limited sensor resolution. We present an algorithm that estimates non-parametric, spatially-varying blur functions (i.e., point-spread functions or PSFs)...
Article
We present a method for simultaneously recovering shape and spatially varying reflectance of a surface from photometric stereo images. The distinguishing feature of our approach is its generality; it does not rely on a specific parametric reflectance model and is therefore purely ldquodata-drivenrdquo. This is achieved by employing novel bi-variate...
Article
Full-text available
This paper presents a practical method for finding the provably globally optimal solution to numerous problems in projective geometry including multiview triangulation, camera resectioning and homography estimation. Unlike traditional methods which may get trapped in local minima due to the non-convex nature of these problems, this approach provide...
Conference Paper
We describe a framework for improving the quality of personal photos by using a person's favorite photographs as examples. We use common faces across images to automatically perform both global and face specific corrections. Our system achieves this by using face detection to align faces between "good" and "bad" photos such that properties of the g...
Conference Paper
We consider the problem of reconstructing the shape of a surface with an arbitrary, spatially varying isotropic bidirectional reflectance distribution function (BRDF), and introduce a novel, stratified photometric stereo method. By using a particular configuration of lights, it is possible to use symmetry in the image measurements resulting from BR...
Chapter
The past decade has seen an increasing interest in the areas of real-time vision, visual tracking, active focus of attention in vision, and vision-based control of motion. Although these topics encompass a diverse set of problems spanning the fields of vision, control, robotics, and artificial intelligence, they all share a common focus: the applic...
Chapter
In the opening chapter, we outlined several areas of research in vision and control, and posed several related questions for discussion. During the Block Island workshop on Vision and Control, these and many related ideas were debated in the formal presentations and discussion periods. The summary reports of these discussions, which can be viewed a...
Conference Paper
We present an autocalibration algorithm for upgrading a projective reconstruction to a metric reconstruction by estimating the absolute dual quadric. The algorithm enforces the rank degeneracy and the positive semidefiniteness of the dual quadric as part of the estimation procedure, rather than as a post-processing step. Furthermore, the method all...
Conference Paper
Full-text available
We present a scalable approach to recognizing and describing complex activities in video sequences. We are interested in long-term, sequential activities that may have several parallel streams of action. Our approach integrates temporal, contextual and ordering constraints with output from low-level visual detectors to recognize complex, long-term...
Article
A set of images of a Lambertian surface under varying lighting directions defines its shape up to a three-parameter Generalized Bas-Relief (GBR) ambiguity. In this paper, we examine this ambiguity in the context of surfaces having an additive non-Lambertian reflectance component, and we show that the GBR ambiguity is resolved by any non-Lambertian...
Conference Paper
We present an algorithm for performing Lambertian pho- tometric stereo in the presence of shadows. The algorithm has three novel features. First, a fast graph cuts based method is used to estimate per pixel light source visibility. Second, it allows images to be acquired with multiple illu- minants, and there can be fewer images than light sources....
Conference Paper
It is well known in the photometric stereo literature that uncalibrated photometric stereo, where light source strength and direction are unknown, can recover the surface geometry of a Lambertian object up to a 3-parameter linear transform known as the generalized bas relief (GBR) ambi- guity. Many techniques have been proposed for resolving the GB...
Article
Full-text available
We consider the non-metric multidimensional scaling problem: given a set of dissimilarities , find an embedding whose inter-point Eu- clidean distances have the same ordering as . In this paper, we look at a generaliza- tion of this problem in which only a set of order relations of the form dij < dkl are pro- vided. Unlike the original problem, the...
Conference Paper
We address the problem of reconstructing the 3-D shape of a Lambertian surface from multiple images acquired as an object rotates under distant and possibly varying illumination. Using camera projection matrices estimated from point correspondences across views, the algorithm computes a dense correspondence map by minimizing a multi-ocular photomet...
Conference Paper
Occlusion is a significant challenge for many tracking algorithms. Most current methods can track through tran- sient occlusion, but cannot handle significant extended oc- clusion when the object's trajectory may change signifi- cantly. We present a method to track a 3D object through significant occlusion using multiple nearby cameras (e.g., a cam...
Conference Paper
Full-text available
We present a practical, stratified autocalibration al- gorithm with theoretical guarantees of global optimality. Given a projective reconstruction, the first stage of the algo- rithm upgrades it to affine by estimating the position of the plane at infinity. The plane at infinity is computed by glob- ally minimizing a least squares formulation of th...
Article
Unconstrained illumination and pose variation lead to significant variation in the photographs of faces and constitute a major hurdle preventing the widespread use of face recognition systems. The challenge is to generalize from a limited number of images of an individual to a broad range of conditions. Recently, advances in modeling the effects of...