3D object detection from LiDAR point cloud is a challenging problem in 3D scene
understanding and has many practical applications. In this paper, we extend our preliminary …

Rapid advances in 2D perception have led to systems that accurately detect objects in real-
world images. However, these systems make predictions in 2D, ignoring the 3D structure of …

While humans easily recognize relations between data from different domains without any
supervision, learning to automatically discover them is in general very challenging and …

Modern neural networks use building blocks such as convolutions that are equivariant to
arbitrary 2 D translations. However, these vanilla blocks are not equivariant to arbitrary 3 D …

Deep neural networks are widely used for classification. These deep models often suffer
from a lack of interpretability---they are particularly difficult to understand because of their …

We study 3D shape modeling from a single image and make contributions to it in three
aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with …

The goal of this paper is to perform 3D object detection in single monocular images in the
domain of autonomous driving. Our method first aims to generate a set of candidate class …

Deep image translation methods have recently shown excellent results, outputting high-
quality images covering multiple modes of the data distribution. There has also been …

Monocular 3D scene understanding tasks, such as object size estimation, heading angle
estimation and 3D localization, is challenging. Successful modern-day methods for 3D …

We present a fast inverse-graphics framework for instance-level 3D scene understanding.
We train a deep convolutional network that learns to map image regions to the full 3D shape …