research
∙
06/05/2023
Learning from Multi-View Representation for Point-Cloud Pre-Training
A critical problem in the pre-training of 3D point clouds is leveraging ...
share
research
∙
01/03/2022
Implicit Autoencoder for Point Cloud Self-supervised Representation Learning
Many 3D representations (e.g., point clouds) are discrete samples of the...
research
∙
08/30/2021
Scene Synthesis via Uncertainty-Driven Attribute Synchronization
Developing deep neural networks to generate 3D scenes is a fundamental p...
research
∙
05/22/2021
HPNet: Deep Primitive Segmentation Using Hybrid Representations
This paper introduces HPNet, a novel deep-learning approach for segmenti...
research
∙
12/25/2019
Extreme Relative Pose Network under Hybrid Representations
In this paper, we introduce a novel RGB-D based relative pose estimation...
research
∙
12/22/2019
Recurrent Feedback Improves Feedforward Representations in Deep Neural Networks
The abundant recurrent horizontal and feedback connections in the primat...
research
∙
02/20/2018