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.
We introduce Appearance-MAT (AMAT), a generalization of the medial axis transform for natural images, that is framed as a weighted geometric set cover problem. We make the following contributions: i) we extend previous medial point detection methods for color images, by associating each medial point with a local scale; ii) inspired by the invertibility property of the binary MAT, we also associate...
In this paper we present a differential approach to photo-polarimetric shape estimation. We propose several alternative differential constraints based on polarisation and photometric shading information and show how to express them in a unified partial differential system. Our method uses the image ratios technique to combine shading and polarisation information in order to directly reconstruct surface...
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...
In 3D reconstruction, the obtained surface details are mainly limited to the visual sensor due to sampling and quantization in the digitalization process. How to get a fine-grained 3D surface with low-cost is still a challenging obstacle in terms of experience, equipment and easyto-obtain. This work introduces a novel framework for enhancing surfaces reconstructed from normal map, where the assumptions...
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...
We present a novel and effective approach for generating new clothing on a wearer through generative adversarial learning. Given an input image of a person and a sentence describing a different outfit, our model “redresses” the person as desired, while at the same time keeping the wearer and her/his pose unchanged. Generating new outfits with precise regions conforming to a language description while...
The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape representation based on primitives. Given a single depth image of an object, we present...
This work introduces a novel surface registration method based on foliation. A foliation decomposes the surface into a family of closed loops, such that the decomposition has local tensor product structure. By projecting each loop to a point, the surface is collapsed into a graph. Two homeomorphic surfaces with consistent foliations can be registered by first matching their foliation graphs, then...
Humans infer rich knowledge of objects from both auditory and visual cues. Building a machine of such competency, however, is very challenging, due to the great difficulty in capturing large-scale, clean data of objects with both their appearance and the sound they make. In this paper, we present a novel, open-source pipeline that generates audiovisual data, purely from 3D object shapes and their...
Electrocorticographic (ECoG) electrode arrays with epidural placement allow establishing neural interfaces which promote investigation of complex distributed brain functions and development of neuroprosthetic systems while having reduced invasiveness in comparison to intracortical or subdural electrode placement. In this work, we present the design and fabrication of a flexible ECoG array with 202...
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...
We propose a joint intrinsic-extrinsic prior model to estimate both illumination and reflectance from an observed image. The 2D image formed from 3D object in the scene is affected by the intrinsic properties (shape and texture) and the extrinsic property (illumination). Based on a novel structure-preserving measure called local variation deviation, a joint intrinsic-extrinsic prior model is proposed...
This work focuses on the design improvement of a tri-axial piezoresistive accelerometer specifically designed for head injuries monitoring where medium-G impacts are common, for example in sports such as racing cars. The device requires the highest sensitivity achievable with a single proof mass approach, and a very low error as the accuracy for these types of applications is paramount. The optimization...
Envelope tracking and asymmetric Doherty power amplifiers are two techniques that can be used to achieve high average efficiencies when amplifying signals with high peak-to-average power ratios, e.g. those employed in modern wireless communication standards. In this paper, a combination of the two techniques, the modulation of the drain voltage of the peaking amplifier in an asymmetric Doherty power...
People can easily perceive object with incompletion boundary or combination of discontinuous edges. However, common approaches are difficult to segment an entire object without referring to completion contour. This paper introduces a scheme to reify an object based on law of closure in Gestalt psychology. The proposed scheme acquires initial boundaries and edges in advance, and then divides boundary...
We present a fragmented piece reconstruction method that enables all non-overlapping and randomly placed fragmented pieces to be identified and gathered piece-by-piece to be placed in the corresponding position. The proposed method can be applied in many other fields such as industrial automation, robot vision, archeology, and art restoration.
Our objective is to create a system that enables users to interact with surrounding surfaces by using touch interactions. In this work, we propose a touch detection method that utilizes the shadows of a finger for use with a system featuring an infrared (IR) camera and two IR lights. Since the shape of a finger's shadow varies depending on the distance between the surface and the finger, the system...
In this paper, a new multiple extended target tracking learning algorithm based on labelled random finite sets (L-RFS) framework is proposed to estimate the number, shape and state of extended targets under clutter conditions. The algorithm mainly includes two aspects: multi-extended target dynamic modeling and multi-extended target tracking estimates. Firstly, a finite mixture model (FMM) of extended...
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.