Search Results for author:
Found 5 papers, 2 papers with code
Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration
Learning universal representations across different applications domain is an open research problem.
Ranked #1 on
Point Cloud Registration
on FPv1
Generalizable Human Pose Triangulation
We propose a stochastic framework for human pose triangulation and demonstrate a superior generalization across different camera arrangements on two public datasets.
Ranked #27 on
3D Human Pose Estimation
on Human3.6M
Catadioptric Stereo on a Smartphone
We present a 3D printed adapter with planar mirrors for stereo reconstruction using front and back smartphone camera.
On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods
Additionally, we analyze the performance of two recent and perspective deep detector-descriptor models, LF-Net and SuperPoint.
Surface Registration Using Genetic Algorithm in Reduced Search Space
Problem of surface registration can be analyzed as an optimization problem of seeking a rigid motion between two different views.
