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 …

Point cloud segmentation is fundamental in understanding 3D environments. However,
current 3D point cloud segmentation methods usually perform poorly on scene boundaries …

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 …

We address efficient and structure-aware 3D scene representation from images. Nerflets are
our key contribution--a set of local neural radiance fields that together represent a scene …

Rapid progress in 3D semantic segmentation is inseparable from the advances of deep
network models, which highly rely on large-scale annotated data for training. To address the …

Multi-view projection methods have demonstrated their ability to reach state-of-the-art
performance on 3D shape recognition. Those methods learn different ways to aggregate …

We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing
methods which primarily rely on a large amount of human annotations for training neural …

Point cloud semantic segmentation often requires largescale annotated training data, but
clearly, point-wise labels are too tedious to prepare. While some recent methods propose to …

Abstract Neural Radiance Fields (NeRF) have recently demonstrated photorealistic results
for the task of novel view synthesis. In this paper, we propose to apply novel view synthesis …