3D Geometry Perception

4 papers with code • 0 benchmarks • 3 datasets

Image: Zhao et al

Most implemented papers

SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception

mengyuest/SIGNet CVPR 2019

SIGNet is shown to improve upon the state-of-the-art unsupervised learning for depth prediction by 30% (in squared relative error).

3D Point Capsule Networks

yongheng1991/3D-point-capsule-networks CVPR 2019

In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.

ACSC: Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems

HViktorTsoi/ACSC 17 Nov 2020

Recently, the rapid development of Solid-State LiDAR (SSL) enables low-cost and efficient obtainment of 3D point clouds from the environment, which has inspired a large quantity of studies and applications.

ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes

brown-ivl/ConDor CVPR 2022

ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds.