Valter Piedade

valter.piedade@tecnico.ulisboa.pt


PhD student at Instituto Superior Técnico (IST) since 2022, working on 3D computer vision. I'm a member of the Institute for Systems and Robotics (ISR | Lisboa) as part of the Intelligent Robots and Systems Laboratory (IRS group). My advisors are Dr. Pedro Miraldo and Prof. José Gaspar.

Since 2020 I have been developing from scratch in C++ a Visual SLAM system for an autonomous mobile robot in a retail store environment using only a fisheye stereo camera. In 2023 I was a teaching assistant of Object Oriented Programming.

I have a BSc and a MSc degree in Electrical and Computer Engineering from IST. My major and minor specializations are Systems, Decision and Control and Computers, respectively.


        

profile photo

News

2023:

  • [11/2023] Participated in PhD Open Days 2023 held at Instituto Superior Técnico.
  • [10/2023] Attended ICCV23 in Paris to present BANSAC: A dynamic BAyesian Network for adaptive SAmple Consensus.
  • [07/2023] 1 paper accepted at the IEEE/CVF Int'l Conf. Computer Vision (ICCV), 2023.

Research and Projects

My research interests focus on computer vision, robotics and artificial intelligence. I'm particularly interested in 3D reconstruction, namely Simultaneous Localization and Mapping (SLAM) systems and Structure-from-Motion (SfM).

BANSAC: A dynamic BAyesian Network for adaptive SAmple Consensus
Valter Piedade, Pedro Miraldo
IEEE/CVF Int'l Conf. Computer Vision (ICCV), 2023
Project page - Paper - arXiv - Video - Poster

BANSAC is a sampling strategy for RANSAC. We derive a dynamic Bayesian network that iteratively updates individual data points' inlier probability. In each iteration, the updated probabilities guide the sampling process. This approach outperforms the best baselines in accuracy, being also more efficient.


Last updated on Apr. 15, 2024. Website source code from Jon Barron.