We present RoboGrammar , a fully automated approach for generating optimized robot structures to traverse given terrains. In this framework, we represent each robot design as a graph, and use a graph grammar to express possible arrangements of physical robot a...

Recent deep image-to-image translation techniques allow fast generation of face images from freehand sketches. However, existing solutions tend to overfit to sketches, thus requiring professional sketches or even edge maps as input. To address this issue, our ...

Human characters with a broad range of natural looking and physically realistic behaviors will enable the construction of compelling interactive experiences. In this paper, we develop a technique for learning controllers for a large set of heterogeneous behavi...

The application of heuristic algorithms with life cycle assessment (LCA) is a promising approach to efficiently optimize the building and minimize the environmental impact even in a very large design space. In this paper, a modular parametric optimization fram...

In this paper we present a learned alternative to the Motion Matching algorithm which retains the positive properties of Motion Matching but additionally achieves the scalability of neural-network-based generative models. Although neural-network-based generati...

Holography is arguably the most promising technology to provide wide field-of-view compact eyeglasses-style near-eye displays for augmented and virtual reality. However, the image quality of existing holographic displays is far from that of current generation ...

Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of luminance, but are not able to halluc...

Security of payment (SOP) issues still persist in the construction industry despite numerous investigations and incremental reforms. Various solutions and policies have been proposed and analysed in-depth in previous studies. However, limited studies have focu...

We present a class of display designs combining holographic optics, directional backlighting, laser illumination, and polarization-based optical folding to achieve thin, lightweight, and high performance near-eye displays for virtual reality. Several design al...

Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics---a triangular mesh---and ask how it can be ...

Differentiable rendering computes derivatives of the light transport equation with respect to arbitrary 3D scene parameters, and enables various applications in inverse rendering and machine learning. We present an unbiased and efficient differentiable renderi...

This paper presents a new approach to robotic fabrication in the building industry through the conceptualization, development and evaluation of a largescale, transportable and flexible robotic timber construction platform – named TIM. Novel solutions are neces...