Reconstruction of a continuous surface of two-dimensional manifold from its raw, discrete
point cloud observation is a long-standing problem in computer vision and graphics …

Indoor environment model reconstruction has emerged as a significant and challenging task
in terms of the provision of a semantically rich and geometrically accurate indoor model …

A key requirement for leveraging supervised deep learning methods is the availability of
large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very …

Current 3D object detection methods are heavily influenced by 2D detectors. In order to
leverage architectures in 2D detectors, they often convert 3D point clouds to regular grids …

Shape completion, the problem of estimating the complete geometry of objects from partial
observations, lies at the core of many vision and robotics applications. In this work, we …

We introduce a data-driven approach to complete partial 3D shapes through a combination
of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input …

Abstract 3D object detection has seen quick progress thanks to advances in deep learning
on point clouds. A few recent works have even shown state-of-the-art performance with just …

The area of surface reconstruction has seen substantial progress in the past two decades.
The traditional problem addressed by surface reconstruction is to recover the digital …

We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D
scan of a scene as input and predicting a complete 3D model along with per-voxel semantic …

We propose a method for the data‐driven inference of temporal evolutions of physical
functions with deep learning. More specifically, we target fluid flow problems, and we …