Multi-beam LiDAR sensors, as used on autonomous vehicles and mobile robots, acquire
sequences of 3D range scans (“frames”). Each frame covers the scene sparsely, due to …

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike
all existing methods which usually require a large amount of human annotations for full …

Abstract We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple,
effective, and robust geometric algorithm that can segment objects in 3D scenes without …

People often use physical intuition when manipulating articulated objects, irrespective of
object semantics. Motivated by this observation, we identify an important embodied task …

We introduce MultiScan, a scalable RGBD dataset construction pipeline leveraging
commodity mobile devices to scan indoor scenes with articulated objects and web-based …

We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by
synchronizing the maps that relate learned functions defined on the point clouds. Even …

Equivariance has gained strong interest as a desirable network property that inherently
ensures robust generalization. However, when dealing with complex systems such as …

Regressing rotations on SO (3) manifold using deep neural networks is an important yet
unsolved problem. The gap between the Euclidean network output space and the non …

We devise a 3D scene graph representation, contact graph+(cg+), for efficient sequential
manipulation planning. Augmented with predicate-like attributes, this contact graph-based …

Research into dynamic 3D scene understanding has primarily focused on short-term change
tracking from dense observations while little attention has been paid to long-term changes …