Robotic perception requires the modeling of both 3D geometry and semantics. Existing
methods typically focus on estimating 3D bounding boxes, neglecting finer geometric details …

Masked Autoencoders learn strong visual representations and achieve state-of-the-art
results in several independent modalities, yet very few works have addressed their …

Masked autoencoding has achieved great success for self-supervised learning in the image
and language domains. However, mask based pretraining has yet to show benefits for point …

We present a novel two-stage fully sparse convolutional 3D object detection framework,
named CAGroup3D. Our proposed method first generates some high-quality 3D proposals …

Abstract We present NeRF-Det, a novel method for indoor 3D detection with posed RGB
images as input. Unlike existing indoor 3D detection methods that struggle to model scene …

Modern 3D semantic instance segmentation approaches predominantly rely on specialized
voting mechanisms followed by carefully designed geometric clustering techniques. Building …

We propose octree-based transformers, named OctFormer, for 3D point cloud learning.
OctFormer can not only serve as a general and effective backbone for 3D point cloud …

Advanced 3D object detection methods usually rely on large-scale, elaborately labeled
datasets to achieve good performance. However, labeling the bounding boxes for the 3D …

In the realm of computer vision and robotics embodied agents are expected to explore their
environment and carry out human instructions. This necessitates the ability to fully …

This paper presents the first significant object detection framework, NeRF-RPN, which
directly operates on NeRF. Given a pre-trained NeRF model, NeRF-RPN aims to detect all …