We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware. We fuse all of the depth data streamed from a Kinect sensor into a single global implicit surface model of the observed scene in real-time. The current sensor pose is simultaneously obtained by tracking the live depth frame relative to the global model using a coarse-to-fine iterative closest point (ICP) algorithm, which uses all of the observed depth data available. We demonstrate the advantages of tracking against the growing full surface model compared with frame-to-frame tracking, obtaining tracking and mapping results in constant time within room sized scenes with limited drift and high accuracy. We also show both qualitative and quantitative results relating to various aspects of our tracking and mapping system. Modelling of natural scenes, in real-time with only commodity sensor and GPU hardware, promises an exciting step forward in augmented reality (AR), in particular, it allows dense surfaces to be reconstructed in real-time, with a level of detail and robustness beyond any solution yet presented using passive computer vision.

/pdf/kinectfusion-real-time-dense-surface-mapping-and-tracking-pl8e8pbmre.pdf

KinectFusion: Real-time dense surface mapping and tracking

Humans perceive the three-dimensional structure of the world with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a computer interpret an image at the same level as a two-year old remains elusive. Why is computer vision such a challenging problem and what is the current state of the art? Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging, and for fun, consumer-level tasks such as image editing and stitching, which students can apply to their own personal photos and videos. More than just a source of recipes, this exceptionally authoritative and comprehensive textbook/reference also takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting them to produce descriptions of a scene. These problems are also analyzed using statistical models and solved using rigorous engineering techniques Topics and features: structured to support active curricula and project-oriented courses, with tips in the Introduction for using the book in a variety of customized courses; presents exercises at the end of each chapter with a heavy emphasis on testing algorithms and containing numerous suggestions for small mid-term projects; provides additional material and more detailed mathematical topics in the Appendices, which cover linear algebra, numerical techniques, and Bayesian estimation theory; suggests additional reading at the end of each chapter, including the latest research in each sub-field, in addition to a full Bibliography at the end of the book; supplies supplementary course material for students at the associated website, http://szeliski.org/Book/. Suitable for an upper-level undergraduate or graduate-level course in computer science or engineering, this textbook focuses on basic techniques that work under real-world conditions and encourages students to push their creative boundaries. Its design and exposition also make it eminently suitable as a unique reference to the fundamental techniques and current research literature in computer vision.

/pdf/computer-vision-algorithms-and-applications-25dn6wu83j.pdf

Computer Vision: Algorithms and Applications

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can only be trained on synthetic data due to the unavailability of large-scale in-the-wild egocentric datasets. Furthermore, these methods easily fail when the body parts are occluded by or interacting with the surrounding scene. To address the shortage of in-the-wild data, we collect a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW). This dataset is captured by a head-mounted fisheye camera and an auxiliary external camera, which provides an additional observation of the human body from a third-person perspective during training. We present a new egocentric pose estimation method, which can be trained on the new dataset with weak external supervision. Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision. The pseudo labels are then used to train an egocentric pose estimation network. To facilitate the network training, we propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. The experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.

Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision

Panoramic imagery is viewed daily by thousands of people, and panoramic video imagery is becoming more common. This imagery is viewed on many different devices with different properties, and the effect of these differences on spatio-temporal task performance is yet untested on these imagery. We adapt a novel panoramic video interface and conduct a user study to discover whether display type affects spatio-temporal reasoning task performance across desktop monitor, tablet, and head-mounted displays. We discover that, in our complex reasoning task, HMDs are as effective as desktop displays even if participants felt less capable, but tablets were less effective than desktop displays even though participants felt just as capable. Our results impact virtual tourism, telepresence, and surveillance applications, and so we state the design implications of our results for panoramic imagery systems.

/pdf/device-effect-on-panoramic-video-context-tasks-24h57655lw.pdf

Device effect on panoramic video+context tasks

3D human motion capture from monocular RGB images respecting interactions of a subject with complex and possibly deformable environments is a very challenging, illposed and under-explored problem. Existing methods address it only weakly and do not model possible surface deformations often occurring when humans interact with scene surfaces. In contrast, this paper proposes MoCapDe-form, i.e., a new framework for monocular 3D human motion capture that is the first to explicitly model non-rigid deformations of a 3D scene for improved 3D human pose estimation and deformable environment reconstruction. Mo-CapDeform accepts a monocular RGB video and a 3D scene mesh aligned in the camera space. It first localises a subject in the input monocular video along with dense contact labels using a new raycasting based strategy. Next, our human-environment interaction constraints are leveraged to jointly optimise global 3D human poses and non-rigid surface deformations. MoCapDeform achieves superior accuracy than competing methods on several datasets, including our newly recorded one with deforming background scenes.

MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes

We present a markerless performance capture system that can acquire the motion and the texture of human actors performing fast movements using only commodity hardware. To this end we introduce two novel concepts: First, a staggered surround multi-view recording setup that enables us to perform model-based motion capture on motion-blurred images, and second, a model-based deblurring algorithm which is able to handle disocclusion, self-occlusion and complex object motions. We show that the model-based approach is not only a powerful strategy for tracking but also for deblurring highly complex blur patterns. © 2012 Wiley Periodicals, Inc.

/pdf/performance-capture-of-high-speed-motion-using-staggered-14148kblu3.pdf

Performance Capture of High-Speed Motion Using Staggered Multi-View Recording

3D Videos of Human Actors can be faithfully reconstructed from multiple synchronized video streams by means of a model-based analysis-by-synthesis approach [Carranza et al. 2003]. The reconstructed videos play back in real-time and the virtual viewpoint onto the scene can be arbitrarily changed. By this means authentically animated, photo-realistically and view-dependently textured models of real people can be created that look real under fixed illumination conditions. To import real-world characters into virtual environments, however, also surface reflectance properties must be known. We have thus developed a video-based modeling approach that captures human motion as well as reflectance characteristics from a handful of synchronized video recordings. The presented method is able to recover spatially varying reflectance properties of clothes by exploiting the time-varying orientation of each surface point with respect to camera and light direction. The resulting model description enables us to match animated subject appearance to different lighting conditions, as well as to interchange surface attributes among different people, e.g. for virtual dressing. Our relightable 3D videos allow populating virtual worlds with convincingly relit real-world people.

Christian Theobalt

Papers

Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision

Device effect on panoramic video+context tasks

MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes

Performance Capture of High-Speed Motion Using Staggered Multi-View Recording

Joint motion and reflectance capture for relightable 3D video