Large vision-language models have achieved outstanding performance, but ...
Single image 3D reconstruction is an important but challenging task that...
We introduce OpenShape, a method for learning multi-modal joint
represen...
Generalizable 3D part segmentation is important but challenging in visio...
Semantic segmentation of LiDAR point clouds is an important task in
auto...
We study how choices of input point cloud coordinate frames impact learn...
Approximate convex decomposition aims to decompose a 3D shape into a set...
In this paper, we focus on the simulation of active stereovision depth
s...
We propose DeepMetaHandles, a 3D conditional generative model based on m...
We are interested in reconstructing the mesh representation of object
su...
Building home assistant robots has long been a pursuit for vision and
ro...
3D point cloud completion, the task of inferring the complete geometric ...
Pre-training is transformative in supervised learning: a large network
t...