Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration

2 code implementations • 29 Nov 2022 • David Bojanić, Kristijan Bartol, Josep Forest, Stefan Gumhold, Tomislav Petković, Tomislav Pribanić

Learning universal representations across different applications domain is an open research problem.

Point Cloud Registration

Generalizable Human Pose Triangulation

no code implementations • CVPR 2022 • Kristijan Bartol, David Bojanić, Tomislav Petković, Tomislav Pribanić

We propose a stochastic framework for human pose triangulation and demonstrate a superior generalization across different camera arrangements on two public datasets.

3D Human Pose Estimation 3D Pose Estimation

Catadioptric Stereo on a Smartphone

no code implementations • 24 Sep 2021 • Kristijan Bartol, David Bojanić, Tomislav Petković, Tomislav Pribanić

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

2 code implementations • 20 Jul 2020 • Kristijan Bartol, David Bojanić, Tomislav Pribanić, Tomislav Petković, Yago Diez Donoso, Joaquim Salvi Mas

Additionally, we analyze the performance of two recent and perspective deep detector-descriptor models, LF-Net and SuperPoint.

Retrieval