1 code implementation • ICCV 2023 • Nathaniel Burgdorfer, Philippos Mordohai
We introduce a learning-based depth map fusion framework that accepts a set of depth and confidence maps generated by a Multi-View Stereo (MVS) algorithm as input and improves them.
no code implementations • 4 Aug 2023 • Weihan Wang, Jiani Li, Yuhang Ming, Philippos Mordohai
Our method incorporates an Error-state Kalman Filter (ESKF) to estimate gyroscope bias and correct rotation estimates from monocular SLAM, overcoming dependence on pure monocular SLAM for rotation estimation.
2 code implementations • 5 Apr 2023 • Weihan Wang, Bharat Joshi, Nathaniel Burgdorfer, Konstantinos Batsos, Alberto Quattrini Li, Philippos Mordohai, Ioannis Rekleitis
To address this problem, we propose to use SVIn2, a robust VIO method, together with a real-time 3D reconstruction pipeline.
1 code implementation • CVPR 2023 • Liyan Chen, Weihan Wang, Philippos Mordohai
We present a new loss function for joint disparity and uncertainty estimation in deep stereo matching.
no code implementations • 6 Sep 2021 • Tejas Mane, Aylar Bayramova, Kostas Daniilidis, Philippos Mordohai, Elena Bernardis
We address the problem of estimating the shape of a person's head, defined as the geometry of the complete head surface, from a video taken with a single moving camera, and determining the alignment of the fitted 3D head for all video frames, irrespective of the person's pose.
1 code implementation • 14 Oct 2020 • Changjiang Cai, Matteo Poggi, Stefano Mattoccia, Philippos Mordohai
End-to-end deep networks represent the state of the art for stereo matching.
1 code implementation • 14 Oct 2020 • Changjiang Cai, Philippos Mordohai
In this paper, we show how deep adaptive filtering and differentiable semi-global aggregation can be integrated in existing 2D and 3D convolutional networks for end-to-end stereo matching, leading to improved accuracy.
no code implementations • 18 Apr 2020 • Matteo Poggi, Fabio Tosi, Konstantinos Batsos, Philippos Mordohai, Stefano Mattoccia
Stereo matching is one of the longest-standing problems in computer vision with close to 40 years of studies and research.
1 code implementation • 4 May 2019 • Bo Sun, Philippos Mordohai
We named this method Oriented Point Sampling (OPS) to contrast with more conventional techniques that require the sampling of three unoriented points to generate plane hypotheses.
1 code implementation • CVPR 2018 • Konstantinos Batsos, Changjiang Cai, Philippos Mordohai
The success of these methods is due to the availability of training data with ground truth; training learning-based systems on these datasets has allowed them to surpass the accuracy of conventional approaches based on heuristics and assumptions.
no code implementations • CVPR 2015 • Charles Freundlich, Michael Zavlanos, Philippos Mordohai
We present an approach for correcting the bias in 3D reconstruction of points imaged by a calibrated stereo rig.
no code implementations • CVPR 2014 • Aristotle Spyropoulos, Nikos Komodakis, Philippos Mordohai
While machine learning has been instrumental to the ongoing progress in most areas of computer vision, it has not been applied to the problem of stereo matching with similar frequency or success.
no code implementations • 24 Dec 2013 • Leizer Teran, Philippos Mordohai
Sometimes points with high curvature may be desirable, while in other cases high curvature may be an indication of noise.