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 …