We present a benchmark for image-based 3D reconstruction. The benchmark sequences
were acquired outside the lab, in realistic conditions. Ground-truth data was captured using …

Visual localization is the task of accurate camera pose estimation in a known scene. It is a
key problem in computer vision and robotics, with applications including self-driving cars …

We present SP-GAN, a new unsupervised sphere-guided generative model for direct
synthesis of 3D shapes in the form of point clouds. Compared with existing models, SP-GAN …

We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo
reconstruction. Taking an arbitrary number of posed images as input, we first produce a set …

Free-viewpoint image-based rendering (IBR) is a standing challenge. IBR methods combine
warped versions of input photos to synthesize a novel view. The image quality of this …

Visual localization, ie, the problem of camera pose estimation, is a central component of
applications such as autonomous robots and augmented reality systems. A dominant …

Drones equipped with cameras are emerging as a powerful tool for large-scale aerial 3D
scanning, but existing automatic flight planners do not exploit all available information about …

We present an algorithm that enables casual 3D photography. Given a set of input photos
captured with a hand-held cell phone or DSLR camera, our algorithm reconstructs a 3D …

Virtual reality headsets are becoming increasingly popular, yet it remains difficult for casual
users to capture immersive 360° VR panoramas. State-of-the-art approaches require …

We present a method for adding parallax and real-time playback of 360° videos in Virtual
Reality headsets. In current video players, the playback does not respond to translational …