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 …

This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view
images. Many previous works have shown impressive reconstruction results on textured …

The recent success of neural networks enables a better interpretation of 3D point clouds, but
processing a large-scale 3D scene remains a challenging problem. Most current …

Scene understanding based on image segmentation is a crucial component of autonomous
vehicles. Pixel-wise semantic segmentation of RGB images can be advanced by exploiting …

Recent works on 3D semantic segmentation propose to exploit the synergy between images
and point clouds by processing each modality with a dedicated network and projecting …

Abstract 3D dense captioning aims to describe individual objects by natural language in 3D
scenes, where 3D scenes are usually represented as RGB-D scans or point clouds …

Despite significant advancements in monocular depth estimation for static images,
estimating video depth in the open world remains challenging, since open-world videos are …

Learning distinctive point-wise features is critical for low-overlap point cloud registration.
Recently, it has achieved huge success in incorporating Transformer into point cloud feature …

Current 3D segmentation methods heavily rely on large-scale point-cloud datasets, which
are notoriously laborious to annotate. Few attempts have been made to circumvent the need …

3D segmentation is a fundamental and challenging problem in computer vision with
applications in autonomous driving and robotics. It has received significant attention from the …