This paper surveys visualization and interaction techniques for geospatial networks from a total of 95 papers.

We present a method to augment parametric skeletal models with subspace soft-tissue deformations.

Recent advances in generative adversarial networks (GANs) have shown tremendous success for facial expression generation tasks.

We specifically present a general method for monocular fluid videos to reconstruct and edit 3D fluid volume.

Division-of-focal-plane (DoFP) polarization image sensors allow for snapshot imaging of linear polarization effects with inexpensive and straightforward setups.

This paper proposes a joint design for snapshot HDR imaging by devising a spatially varying modulation mask in the hardware and building a deep learning algorithm to reconstruct the HDR image.

Part mobility analysis is a significant aspect required to achieve a functional understanding of 3D objects.

Scale-invariant integral surfaces, which are implicit representations of surfaces, provide a way to define smooth surfaces from skeletons with prescribed radii defined at their vertices. We introduce a new rendering pipeline allowing to visualize such surfaces in real-time.

Tensors are used to describe complex physical processes in many applications.

We present the iterative medial axis transform (IMAT), an iterative descent method that constructs a medial axis transform (MAT) for a sparse, noisy, oriented point cloud sampled from an object's boundary.

Man-made objects commonly exhibit rounded edges and corners. The variation of surface normals at these locations produces shading details essential to the realism of synthetic scenes. The more specular the surface, the finer and more prominent its highlights. Most geometric modelers represent rounded edges and corners with dense polygonal meshes that are limited in terms of smoothness increasing scene complexity. This paper proposes a method for the efficient modeling and rendering of smooth edges and corners from any input polygonal geometry. Our contribution is a geometric structure that automatically and accurately defines the geometry of edge and corner rounded areas, as well as the topological relationships at edges and vertices. This structure (SREC-RT) is integrated in a ray-tracing-based acceleration structure in order to determine the region of interest of each rounded edge and corner. It allows systematic rounding of all edges and vertices without increasing the 3D scene geometric complexity. While the underlying rounded geometry can be of any type, we propose a ray-edge and ray-corner intersection based on parametric surfaces. Our results present the advantages of our method, including extreme close-up views of surfaces with a much higher quality for very little additional memory, and reasonable computation time overhead.

An efficient surface reconstruction strategy is presented in this study, which is able to approximate non-convex sets of target points (TPs).

Despite the rapid development and proliferation of computer graphics hardware devices for scene capture in the most recent decade, the high-resolution 3D/4D acquisition of gaseous scenes (e.g., smokes) in real time remains technically challenging in graphics research nowadays.

Graphical Abstract:

This paper presents a new method for generating simulation-ready garment models from 3D static scan data of clothed humans. A key contribution of our method is a novel approach to segmenting garments by finding optimal boundaries between the skin and garment.

We improve the sampling-based motion control method proposed by Liu et al. using inverse dynamics. The figure shows samples drawn for different frames of a jumping motion. The orange is the reference motion. The blue shows the samples drawn by our method (with sample covariance initialization) and the red shows the samples drawn by our implementation of the sampling-based motion control method. With the use of inverse dynamics torques and sample covariance initialization, our sample simulations can have higher success rates, and we can choose to draw control samples from tighter distributions to produce smoother results.

This contribution reviews the current advances in the application of deep neural computing to illumination estimation and relighting. We examine in detail the attributes of the proposed approaches, presented in three categories: scene illumination estimation, relighting with reflectance-aware scene-specific representations and finally relighting as image-to-image transformations. We also provide an overview of current publicly available datasets for neural lighting applications.

We present a compact neural network-based representation for measured BRDF data that combines high-accuracy reconstruction with efficient rendering via built-in interpolation of reflectance. Additionally, we implement a meta-learning autoencoder architecture that learns the space of real-world materials and generates compact embeddings, which we leverage for material generation through interpolation and efficient rendering via importance sampling.

A visual comparison of various summarization methods. From left to right: classical sampling, clustering, contour trees, and CS-ADMM. CS-ADMM is able to distribute elements that are both fit and diverse. Our visualization scheme encodes high fitness values as dark red and low fitness values as dark blue. The individual elements are shown as black dots.

We present a neural-based model for relighting a half-body portrait image by simply referring to another portrait image with the desired lighting condition.

We present a method for the efficient processing of contact and collision in volumetric elastic models simulated using the Projective Dynamics paradigm.

We present an approach that is able to calculate several important properties from arbitrarily large protein-ligand interaction data and display them interactively. Furthermore, our web-based visualisation framework shows the extracted properties in a surface view as well as in our newly introduced Compressed Ligand Interaction Sequence Diagram.

In this paper we present a novel method for recovering high-resolution spatially-varying isotropic surface reflectance of a planar exemplar from a flash-lit close-up video sequence captured with a regular hand-held mobile phone.

Rendering a church point cloud (input) with the colour style of a fantasy house point cloud (target) using our colour transfer method.

This paper reports the design and comparison of three visualizations to represent the structure and content within arguments.

Our approach takes as input a single, annotated fashion drawing and synthesizes a 3D garment of similar style over any existing 3D character. The method handles deep folds and automatically adapts the garment to the morphology and pose of the target, allowing to easily dress human-looking to cartoon-style models.

This paper describes the design and implementation of a web-based system to visualize large collections of text conversations integrated into a hierarchical four-level-of-detail design.

Image editing is a commonly studied problem in computer graphics.