To improve the performance of particle image velocimetry in measuring instantaneous velocity fields, direct cross-correlation of image fields can be used in place of auto-correlation methods of interrogation of double- or multiple-exposure recordings. With improved speed of photographic recording and increased resolution of video array detectors, cross-correlation methods of interrogation of successive single-exposure frames can be used to measure the separation of pairs of particle images between successive frames. By knowing the extent of image shifting used in a multiple-exposure and by a priori knowledge of the mean flow-field, the cross-correlation of different sized interrogation spots with known separation can be optimized in terms of spatial resolution, detection rate, accuracy and reliability.

Theory of cross-correlation analysis of PIV images : Image analysis as measuring technique in flows

In the past two decades, augmented reality (AR) has received a growing amount of attention by researchers in the manufacturing technology community, because AR can be applied to address a wide range of problems throughout the assembly phase in the lifecycle of a product, e.g., planning, design, ergonomics assessment, operation guidance and training. However, to the best of authors’ knowledge, there has not been any comprehensive review of AR-based assembly systems. This paper aims to provide a concise overview of the technical features, characteristics and broad range of applications of AR-based assembly systems published between 1990 and 2015. Among these selected articles, two thirds of them were published between 2005 and 2015, and they are considered as recent pertinent works which will be discussed in detail. In addition, the current limitation factors and future trends in the development will also be discussed.

/pdf/a-comprehensive-survey-of-augmented-reality-assembly-4v9flaozri.pdf

A comprehensive survey of augmented reality assembly research

Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain complex phenomena such as thin structures, evolving topology, translucency, scattering, occlusion, and biological motion. Mesh-based reconstruction and tracking often fail in these cases, and other approaches (e.g., light field video) typically rely on constrained viewing conditions, which limit interactivity. We circumvent these difficulties by presenting a learning-based approach to representing dynamic objects inspired by the integral projection model used in tomographic imaging. The approach is supervised directly from 2D images in a multi-view capture setting and does not require explicit reconstruction or tracking of the object. Our method has two primary components: an encoder-decoder network that transforms input images into a 3D volume representation, and a differentiable ray-marching operation that enables end-to-end training. By virtue of its 3D representation, our construction extrapolates better to novel viewpoints compared to screen-space rendering techniques. The encoder-decoder architecture learns a latent representation of a dynamic scene that enables us to produce novel content sequences not seen during training. To overcome memory limitations of voxel-based representations, we learn a dynamic irregular grid structure implemented with a warp field during ray-marching. This structure greatly improves the apparent resolution and reduces grid-like artifacts and jagged motion. Finally, we demonstrate how to incorporate surface-based representations into our volumetric-learning framework for applications where the highest resolution is required, using facial performance capture as a case in point.

Neural volumes: learning dynamic renderable volumes from images

We present a novel approach for the automatic creation of a personalized high-quality 3D face rig of an actor from just monocular video data (e.g., vintage movies). Our rig is based on three distinct layers that allow us to model the actor’s facial shape as well as capture his person-specific expression characteristics at high fidelity, ranging from coarse-scale geometry to fine-scale static and transient detail on the scale of folds and wrinkles. At the heart of our approach is a parametric shape prior that encodes the plausible subspace of facial identity and expression variations. Based on this prior, a coarse-scale reconstruction is obtained by means of a novel variational fitting approach. We represent person-specific idiosyncrasies, which cannot be represented in the restricted shape and expression space, by learning a set of medium-scale corrective shapes. Fine-scale skin detail, such as wrinkles, are captured from video via shading-based refinement, and a generative detail formation model is learned. Both the medium- and fine-scale detail layers are coupled with the parametric prior by means of a novel sparse linear regression formulation. Once reconstructed, all layers of the face rig can be conveniently controlled by a low number of blendshape expression parameters, as widely used by animation artists. We show captured face rigs and their motions for several actors filmed in different monocular video formats, including legacy footage from YouTube, and demonstrate how they can be used for 3D animation and 2D video editing. Finally, we evaluate our approach qualitatively and quantitatively and compare to related state-of-the-art methods.

Reconstruction of Personalized 3D Face Rigs from Monocular Video

The computer graphics and vision communities have dedicated long standing efforts in building computerized tools for reconstructing, tracking, and analyzing human faces based on visual input. Over the past years rapid progress has been made, which led to novel and powerful algorithms that obtain impressive results even in the very challenging case of reconstruction from a single RGB or RGB‐D camera. The range of applications is vast and steadily growing as these technologies are further improving in speed, accuracy, and ease of use.

State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications

Clouds are important components of the fascinating natural images. However, extracting cloud shapes from images remains a challenging task. This paper presents a calculation method for estimating the shape of a cumulus cloud from a single image suitable for flight simulations and games. The shape of the cloud is assumed to be symmetric. Based on this assumption, the intensities of pixels are correlated with the geometry of a cloud's surface via a simplified single scattering model. A propagation scheme is designed to derive the surface progressively, and mesh editing techniques are used to improve the surface. Finally, the cloud is represented by a particle system. The results show that the proposed method can generate realistic cumulus clouds that are similar to those found in the images in terms of the shape distribution.

Modelling Cumulus Cloud Shape from a Single Image

Dynamic hair strands have complex structures and experience intricate collisions and occlusion, posing significant challenges for high-quality reconstruction of their motions. We present a comprehensive dynamic hair capture system for reconstructing realistic hair motions from multiple synchronized video sequences. To recover hair strands' temporal correspondence, we propose a motion-path analysis algorithm that can robustly track local hair motions in input videos. To ensure the spatial and temporal coherence of the dynamic capture, we formulate the global hair reconstruction as a spacetime optimization problem solved iteratively. Demonstrated using a range of real-world hairstyles driven by different wind conditions and head motions, our approach is able to reconstruct complex hair dynamics matching closely with video recordings both in terms of geometry and motion details.

/pdf/dynamic-hair-capture-using-spacetime-optimization-1raol04w2r.pdf

Dynamic hair capture using spacetime optimization

Recent advances in laser scanning technology have made it possible to faithfully scan a real object with tiny geometric details, such as pores and wrinkles. However, a faithful digital model should not only capture static details of the real counterpart but also be able to reproduce the deformed versions of such details. In this paper, we develop a data-driven model that has two components respectively accommodating smooth large-scale deformations and high-resolution deformable details. Large-scale deformations are based on a nonlinear mapping between sparse control points and bone transformations. A global mapping, however, would fail to synthesize realistic geometries from sparse examples, for highly-deformable models with a large range of motion. The key is to train a collection of mappings defined over regions locally in both the geometry and the pose space. Deformable fine-scale details are generated from a second nonlinear mapping between the control points and per-vertex displacements. We apply our modeling scheme to scanned human hand models. Experiments show that our deformation models, learned from extremely sparse training data, are effective and robust in synthesizing highly-deformable models with rich fine features, for keyframe animation as well as performance-driven animation. We also compare our results with those obtained by alternative techniques.

/pdf/controllable-hand-deformation-from-sparse-examples-with-rich-413kvzbq9r.pdf

Controllable hand deformation from sparse examples with rich details

This paper presents a novel modeling framework to build 3D models of Chinese architectures from elevation drawing. Our algorithm integrates the capability of automatic drawing recognition with powerful procedural modeling to extract production rules from elevation drawing. First, different from the previous symbol-based floor plan recognition, based on the novel concept of repetitive pattern trees, small horizontal repetitive regions of the elevation drawing are clustered in a bottom-up manner to form architectural components with maximum repetition, which collectively serve as building blocks for 3D model generation. Second, to discover the global architectural structure and its components' interdependencies, the components are structured into a shape tree in a top-down subdivision manner and recognized hierarchically at each level of the shape tree based on Markov Random Fields (MRFs). Third, shape grammar rules can be derived to construct 3D semantic model and its possible variations with the help of a 3D component repository. The salient contribution lies in the novel integration of procedural modeling with elevation drawing, with a unique application to Chinese architectures.

/pdf/drawing-based-procedural-modeling-of-chinese-architectures-4ybtzw1l8x.pdf

Drawing-Based Procedural Modeling of Chinese Architectures

In this paper, a compression method of encoding/decoding 3D mesh based on octree is proposed. Vertices of the 3D mesh are reclassified according to the octree rule. We analyse all the nodes of the octree statistically to identify the type of nodes which accounts for the max proportion and encode them with fewer bits. According to the transmission sequence of geometric information, we rearrange topology and attribute information and encode them. Progressive strategies adopted by the single model and the scene are different in order to maximize the use of network bandwidth and computational performance of local machines. This method has high compression rate, is adapt to network transmission with short response time at the client and can control the level of detail of the model decoding.

Yue Qi

Papers

Modelling Cumulus Cloud Shape from a Single Image

Dynamic hair capture using spacetime optimization

Controllable hand deformation from sparse examples with rich details

Drawing-Based Procedural Modeling of Chinese Architectures

3D data codec and transmission over the internet