The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A sequential space carving method has been developed for the 3-D reconstruction of objects from multitude of forward-look sonar images captured at known sonar poses [1]. The 3-D space within common viewing volume of several camera poses is divided into small volumetric pixels (voxels). Projecting each onto various images, all voxels satisfying certain consistency measure are maintained. Conversely,...
Analyzing fish and fish schools behavior can help in studying fish-fish interaction, analyzing characteristics of fish species, studying prey avoidance maneuvers of fish schools, etc. Such analysis requires the estimation of each fish's 3D location, 3D pose, and 3D shape over time. Moreover if we are interested in studying the interaction of fish by injecting visual / acoustic stimuli artificially...
We propose a robust hand pose estimation method by learning hand articulations from depth features and auxiliary modality features. As an additional modality to depth data, we present a function of geometric properties on the surface of the hand described by heat diffusion. The proposed heat distribution descriptor is robust to identify the keypoints on the surface as it incorporates both the local...
Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of “maximizing rigidity” in structure-from-motion literature, and develop a unified theory which is applicable...
Despite recent advances in face recognition using deep learning, severe accuracy drops are observed for large pose variations in unconstrained environments. Learning pose-invariant features is one solution, but needs expensively labeled large-scale data and carefully designed feature learning algorithms. In this work, we focus on frontalizing faces in the wild under various head poses, including extreme...
Simulation results are not representative of a real system behavior up to its model validation. Validation activity needs a model characterization to match real system and model parameters. This activity impacts more on mechatronics systems which are affected by both physical and control characterizations. This work deals with single bowden power window systems; it improves a system model, previously...
Mixed reality (MR) technologies can virtually change the appearance of real objects in real time without changing the material attributes of the objects and the associated haptic stimuli. In this study, we use MR-based visuo—haptic to investigate the mechanisms by which vision and haptics interact. In contrast to MR, diminished reality (DR) can virtually erase a real object from our sight. Because...
This work presents a procedural modeling technique based on shape grammars for representing and rendering massive 3D CAD models in real time. Procedural modeling is an appealing approach to quickly generate massive scenes while maintaining compact representation. Until now, procedural modeling has not been explored in the domain of large industrial projects. Traditional procedural modeling techniques...
Fast and robust 3D reconstruction of facial geometric structure from a single image is a challenging task with numerous applications, but there exist two problems when applied "in the wild": the 3D estimates are unstable for different photos of the same subject; the 3D estimates are over-regularized and generic. In response, a robust method for regressing discriminative 3D morphable face...
We present a fully automatic pipeline to train 3D Morphable Models (3DMMs), with contributions in pose normalisation, dense correspondence using both shape and texture information, and high quality, high resolution texture mapping. We propose a dense correspondence system, combining a hierarchical parts-based template morphing framework in the shape channel and a refining optical flow in the texture...
Traditional approaches for learning 3D object categories use either synthetic data or manual supervision. In this paper, we propose a method which does not require manual annotations and is instead cued by observing objects from a moving vantage point. Our system builds on two innovations: a Siamese viewpoint factorization network that robustly aligns different videos together without explicitly comparing...
We present a new deep learning architecture (called Kdnetwork) that is designed for 3D model recognition tasks and works with unstructured point clouds. The new architecture performs multiplicative transformations and shares parameters of these transformations according to the subdivisions of the point clouds imposed onto them by kdtrees. Unlike the currently dominant convolutional architectures that...
We present the first image-based generative model of people in clothing for the full body. We sidestep the commonly used complex graphics rendering pipeline and the need for high-quality 3D scans of dressed people. Instead, we learn generative models from a large image database. The main challenge is to cope with the high variance in human pose, shape and appearance. For this reason, pure image-based...
Facial alignment involves finding a set of landmark points on an image with a known semantic meaning. However, this semantic meaning of landmark points is often lost in 2D approaches where landmarks are either moved to visible boundaries or ignored as the pose of the face changes. In order to extract consistent alignment points across large poses, the 3D structure of the face must be considered in...
The technique of Projection Mapping, which is useful for merging real-world geometry with an augmented appearance, is a promising core technology for augmented reality (AR). In recent years, dynamically changing environments, mainly a consequence of the growing demand for interactive user experiences, have contributed to a new style of AR applications. However, performance levels of current systems...
The recent boom in the field of virtual and augmented reality has dramatically increased the prevalence of spherical video. Given the enormous amount of data consumed by spherical video, it is critical to achieve efficient compression for storage and transmission. Prevalent approaches simply project (via different geometries) the spherical video onto planes for processing with traditional 2D video...
In total hip arthroplasty, a placement of stem, which is one of the parts of the artificial hip joint, is even difficult for skilled operators. An optimum location of stem is different for each patient. No system for specifying the optimum location has been established. We pay attention to the method using ultrasound in consideration of portability and high introduction ratio to the medical field...
The erosion of contact material is one of the critical failure mechanisms in switch devices. Thus it is important to study the characteristics of contact erosion. In this paper, a two-dimensional magnetic hydrodynamics (MHD) is established to get physical characteristics of the molten pool in cathode. Gas dynamics and statistical methods are then used for the calculation of the vaporization rates...
Recent advances in convolutional neural networks have shown promising results in 3D shape completion. But due to GPU memory limitations, these methods can only produce low-resolution outputs. To inpaint 3D models with semantic plausibility and contextual details, we introduce a hybrid framework that combines a 3D Encoder-Decoder Generative Adversarial Network (3D-ED-GAN) and a Longterm Recurrent Convolutional...
Deep neural networks (DNNs) trained on large-scale datasets have recently achieved impressive improvements in face recognition. But a persistent challenge remains to develop methods capable of handling large pose variations that are relatively under-represented in training data. This paper presents a method for learning a feature representation that is invariant to pose, without requiring extensive...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.