Obtaining high-quality 3D reconstructions of room-scale scenes is of paramount importance
for upcoming applications in AR or VR. These range from mixed reality applications for …

Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain
complex phenomena such as thin structures, evolving topology, translucency, scattering …

We study the notion of consistency between a 3D shape and a 2D observation and propose
a differentiable formulation which allows computing gradients of the 3D shape given an …

We present a learnt system for multi-view stereopsis. In contrast to recent learning based
methods for 3D reconstruction, we leverage the underlying 3D geometry of the problem …

Abstract 3D reconstruction of scenes using multiple images, relying on robust
correspondence search and depth estimation, has been thoroughly studied for the two‐view …

Recently, Convolutional Neural Networks have shown promising results for 3D geometry
prediction. They can make predictions from very little input data such as a single color …

We present a framework for learning single-view shape and pose prediction without using
direct supervision for either. Our approach allows leveraging multi-view observations from …

Robust data association is a core problem of visual odometry, where image-to-image
correspondences provide constraints for camera pose and map estimation. Current state-of …

The efficient fusion of depth maps is a key part of most state-of-the-art 3D reconstruction
methods. Besides requiring high accuracy, these depth fusion methods need to be scalable …

We present a novel online depth map fusion approach that learns depth map aggregation in
a latent feature space. While previous fusion methods use an explicit scene representation …