sunbirddy Goto Github PK

followers: 0.0 following: 6.0 repos: 225.0 gists: 1.0

Type: User

Bio: I'm a phd student in the field of computer vision. My research topic focus on 3D reconstruction.

sunbirddy's Projects

3dfeatnet

3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

3dmatch-toolbox

3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.

3dsmoothnet

[CVPR19] The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

Multi Stage Convolutional Neural Network Based 6D Pose Estimation. In this repo, I provide code for my [IROS 2018 ]paper, "Detect Globally, Label Locally: Learning Accurate 6-DOF Object Pose Estimation by Joint Segmentation and Coordinate Regression". Paper proposes a deep architecture with an instance-level object segmentation network that exploits global image information for object/background segmentation and a pixel-level classification network for coordinate regression based on local features. We evaluate our approach on the standard ground-truth 6-DOF pose estimation benchmarks and show that our joint approach to accurate object segmentation and coordinate regression results in the state-of-the-art performance on both RGB and RGB-D 6-DOF pose estimation.

aaai2018_cl

Partial Multi-view Outlier Detection Based on Collective Learning

academic-responsive-template

Academic Responsive (AR) Website Template

acmh

A simple yet effective PatchMatch MVS method, which is the base model of ACMM and ACMP.

acmm

Multi-Scale Geometric Consistency Guided Multi-View Stereo

acmp

Planar Prior Assisted PatchMatch Multi-View Stereo

adalam

AdaLAM is a fully handcrafted realtime outlier filter integrating several best practices into a single efficient and effective framework. It detects inliers by searching for significant local affine patterns in image correspondences.