Active simultaneous localization and map** (SLAM) is the problem of planning and
controlling the motion of a robot to build the most accurate and complete model of the …

Point cloud learning has lately attracted increasing attention due to its wide applications in
many areas, such as computer vision, autonomous driving, and robotics. As a dominating …

Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a
model for a single task with supervision. We propose OpenScene, an alternative approach …

We introduce DMTet, a deep 3D conditional generative model that can synthesize high-
resolution 3D shapes using simple user guides such as coarse voxels. It marries the merits …

Neural radiance fields (NeRF) encode a scene into a neural representation that enables
photo-realistic rendering of novel views. However, a successful reconstruction from RGB …

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or
noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D …

Semantic scene understanding is important for various applications. In particular, self-driving
cars need a fine-grained understanding of the surfaces and objects in their vicinity. Light …

Recently, the advancement of deep learning (DL) in discriminative feature learning from 3-D
LiDAR data has led to rapid development in the field of autonomous driving. However …

Training deep models for semantic scene completion is challenging due to the sparse and
incomplete input, a large quantity of objects of diverse scales as well as the inherent label …

In recent years, neural implicit representations gained popularity in 3D reconstruction due to
their expressiveness and flexibility. However, the implicit nature of neural implicit …