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

Marker-less 3D human motion capture from a single colour camera has seen significant progress. However, it is a very challenging and severely ill-posed problem. In consequence, even the most accurate state-of-the-art approaches have significant limitations. Purely kinematic formulations on the basis of individual joints or skeletons, and the frequent frame-wise reconstruction in state-of-the-art methods greatly limit 3D accuracy and temporal stability compared to multi-view or marker-based motion capture. Further, captured 3D poses are often physically incorrect and biomechanically implausible, or exhibit implausible environment interactions (floor penetration, foot skating, unnatural body leaning and strong shifting in depth), which is problematic for any use case in computer graphics. We, therefore, present PhysCap, the first algorithm for physically plausible, real-time and marker-less human 3D motion capture with a single colour camera at 25 fps. Our algorithm first captures 3D human poses purely kinematically. To this end, a CNN infers 2D and 3D joint positions, and subsequently, an inverse kinematics step finds space-time coherent joint angles and global 3D pose. Next, these kinematic reconstructions are used as constraints in a real-time physics-based pose optimiser that accounts for environment constraints (e.g., collision handling and floor placement), gravity, and biophysical plausibility of human postures. Our approach employs a combination of ground reaction force and residual force for plausible root control, and uses a trained neural network to detect foot contact events in images. Our method captures physically plausible and temporally stable global 3D human motion, without physically implausible postures, floor penetrations or foot skating, from video in real time and in general scenes. PhysCap achieves state-of-the-art accuracy on established pose benchmarks, and we propose new metrics to demonstrate the improved physical plausibility and temporal stability.

/pdf/physcap-physically-plausible-monocular-3d-motion-capture-in-mt25yfnbwp.pdf

PhysCap: physically plausible monocular 3D motion capture in real time

This paper presents a marker-less method for full body human performance capture by analyzing shading information from a sequence of multi-view images, which are recorded under uncontrolled and changing lighting conditions. Both the articulated motion of the limbs and then the fine-scale surface detail are estimated in a temporally coherent manner. In a temporal framework, differential 3D human pose-changes from the previous time-step are expressed in terms of constraints on the visible image displacements derived from shading cues, estimated albedo and estimated scene illumination. The incident illumination at each frame are estimated jointly with pose, by assuming the Lambertian model of reflectance. The proposed method is independent of image silhouettes and training data, and is thus applicable in cases where background segmentation cannot be performed or a set of training poses is unavailable. We show results on challenging cases for pose-tracking such as changing backgrounds, occlusions and changing lighting conditions.

/pdf/full-body-performance-capture-under-uncontrolled-and-varying-3kk7dmpldh.pdf

Full body performance capture under uncontrolled and varying illumination: a shading-based approach

The acquisition of human motion data is of major importance for creating interactive virtual environments, intelligent user interfaces, and realistic computer animations. Today's performance of off-the-shelf computer hardware enables marker-free non-intrusive optical tracking of the human body. In addition, recent research shows that it is possible to efficiently acquire and render volumetric scene representations in real-time. This paper describes a system to capture human motion at interactive frame rates without the use of markers or scene-intruding devices. Instead, 2D computer vision and 3D volumetric scene reconstruction algorithms are applied directly to the image data. A person is recorded by multiple synchronized cameras, and a multilayer hierarchical kinematic skeleton is fitted to each frame in a two-stage process. We present results with a prototype system running on two PCs.

Combining 2D feature tracking and volume reconstruction for online video-based human motion capture

We present a novel approach to create relightable free-viewpoint human performances from multi-view video recorded under general uncontrolled and uncalibated illumination. We first capture a multi-view sequence of an actor wearing arbitrary apparel and reconstruct a spatio-temporal coherent coarse 3D model of the performance using a marker-less tracking approach. Using these coarse reconstructions, we estimate the low-frequency component of the illumination in a spherical harmonics (SH) basis as well as the diffuse reflectance, and then utilize them to estimate the dynamic geometry detail of human actors based on shading cues. Given the high-quality time-varying geometry, the estimated illumination is extended to the all-frequency domain by re-estimating it in the wavelet basis. Finally, the high-quality all-frequency illumination is utilized to reconstruct the spatially-varying BRDF of the surface. The recovered time-varying surface geometry and spatially-varying non-Lambertian reflectance allow us to generate high-quality model-based free view-point videos of the actor under novel illumination conditions. Our method enables plausible reconstruction of relightable dynamic scene models without a complex controlled lighting apparatus, and opens up a path towards relightable performance capture in less constrained environments and using less complex acquisition setups.

Capturing Relightable Human Performances under General Uncontrolled Illumination

Synthesizing realistic videos of humans using neural networks has been a popular alternative to the conventional graphics-based rendering pipeline due to its high efficiency. Existing works typically formulate this as an image-to-image translation problem in 2D screen space, which leads to artifacts such as over-smoothing, missing body parts, and temporal instability of fine-scale detail, such as pose-dependent wrinkles in the clothing. In this paper, we propose a novel human video synthesis method that approaches these limiting factors by explicitly disentangling the learning of time-coherent fine-scale details from the embedding of the human in 2D screen space. More specifically, our method relies on the combination of two convolutional neural networks (CNNs). Given the pose information, the first CNN predicts a dynamic texture map that contains time-coherent high-frequency details, and the second CNN conditions the generation of the final video on the temporally coherent output of the first CNN. We demonstrate several applications of our approach, such as human reenactment and novel view synthesis from monocular video, where we show significant improvement over the state of the art both qualitatively and quantitatively.

Christian Theobalt

Papers

PhysCap: physically plausible monocular 3D motion capture in real time

Full body performance capture under uncontrolled and varying illumination: a shading-based approach

Combining 2D feature tracking and volume reconstruction for online video-based human motion capture

Capturing Relightable Human Performances under General Uncontrolled Illumination

Neural Human Video Rendering by Learning Dynamic Textures and Rendering-to-Video Translation.