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 …

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 …

The modern computer graphics pipeline can synthesize images at remarkable visual quality;
however, it requires well-defined, high-quality 3D content as input. In this work, we explore …

We present Co-SLAM, a neural RGB-D SLAM system based on a hybrid representation, that
performs robust camera tracking and high-fidelity surface reconstruction in real time. Co …

Real-time, high-quality, 3D scanning of large-scale scenes is key to mixed reality and robotic
applications. However, scalability brings challenges of drift in pose estimation, introducing …

We propose a dense neural simultaneous localization and map** (SLAM) approach for
monocular RGBD input which anchors the features of a neural scene representation in a …

We present a novel approach to real-time dense visual SLAM. Our system is capable of
capturing comprehensive dense globally consistent surfel-based maps of room scale …

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 …

We present a novel approach to real-time dense visual simultaneous localisation and
map**. Our system is capable of capturing comprehensive dense globally consistent …

Online 3D reconstruction is gaining newfound interest due to the availability of real-time
consumer depth cameras. The basic problem takes live overlap** depth maps as input …