research
∙
06/24/2022
HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction
Reconstructing 3D objects is an important computer vision task that has ...
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
∙
05/22/2021
HPNet: Deep Primitive Segmentation Using Hybrid Representations
This paper introduces HPNet, a novel deep-learning approach for segmenti...
research
∙
04/27/2021
MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions
Deep learning has made significant impacts on multi-view stereo systems....
research
∙
05/08/2020
SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
Autonomous driving system development is critically dependent on the abi...
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
∙
12/31/2018
Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
Estimating the relative rigid pose between two RGB-D scans of the same u...
research
∙
08/06/2018