The ability to predict, anticipate and reason about future outcomes is a key component of
intelligent decision-making systems. In light of the success of deep learning in computer …

For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-
pixel ground truth labels from real images. We address this challenge by introducing …

We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions
at room and building scale. Each scene consists of a dense mesh, high-resolution high …

We introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural
world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from …

Abstract We introduce 3D-FRONT (3D Furnished Rooms with layOuts and semaNTics), a
new, large-scale, and compre-hensive repository of synthetic indoor scenes highlighted by …

We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input
image. The training data consists of a texture-mapped 3D object model or images of the …

Recent research in embodied AI has been boosted by the use of simulation environments to
develop and train robot learning approaches. However, the use of simulation has skewed …

Existing work on VQA explores data augmentation to achieve better generalization by
perturbing the images in the dataset or modifying the existing questions and answers. While …

In mobile manipulation (MM), robots can both navigate within and interact with their
environment and are thus able to complete many more tasks than robots only capable of …

Abstract We introduce Infinigen Indoors a Blender-based procedural generator of
photorealistic indoor scenes. It builds upon the existing Infinigen system which focuses on …