no code implementations • 17 Apr 2024 • Chengyang Yan, Donald G. Dansereau
With cameras playing a pivotal role in robotic perception, we introduce a novel end-to-end optimization approach for co-designing a camera with specific robotic tasks by combining derivative-free and gradient-based optimizers.
no code implementations • 12 Apr 2024 • Ryan Griffiths, Donald G. Dansereau
The issue arises that these large-FOV images can't be rectified to a perspective projection without significant cropping of the original image.
no code implementations • 29 Mar 2023 • Adam K. Taras, Niko Suenderhauf, Peter Corke, Donald G. Dansereau
Vision is a popular and effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, gender, identity, activity and even emotional state of humans within that scene.
no code implementations • 14 Oct 2022 • Ryan Griffiths, Jack Naylor, Donald G. Dansereau
This work represents a key step toward automating the interpretation of general camera geometries and emerging imaging technologies.
no code implementations • 20 Sep 2022 • Ahalya Ravendran, Mitch Bryson, Donald G. Dansereau
Robots operating at night using conventional vision cameras face significant challenges in reconstruction due to noise-limited images.
no code implementations • 17 May 2022 • Tristan Frizza, Donald G. Dansereau, Nagita Mehr Seresht, Michael Bewley
This work addresses the problems of semantic segmentation and image super-resolution by jointly considering the performance of both in training a Generative Adversarial Network (GAN).
no code implementations • 23 Aug 2021 • Ahalya Ravendran, Mitch Bryson, Donald G. Dansereau
Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail.
no code implementations • 29 Mar 2021 • Dorian Tsai, Peter Corke, Thierry Peynot, Donald G. Dansereau
Curved refractive objects are common in the human environment, and have a complex visual appearance that can cause robotic vision algorithms to fail.
no code implementations • 21 Mar 2021 • S. Tejaswi Digumarti, Joseph Daniel, Ahalya Ravendran, Donald G. Dansereau
We anticipate our technique to generalise to a broad class of LF and sparse LF cameras, and to enable unsupervised recalibration for coping with shifts in camera behaviour over the lifetime of a robot.
no code implementations • 23 Sep 2020 • Taihua Wang, Donald G. Dansereau
We use the light stage to model and synthetically relight training samples, and propose a greedy pattern selection scheme that exploits this ability to train in simulation.
1 code implementation • CVPR 2019 • Donald G. Dansereau, Bernd Girod, Gordon Wetzstein
Feature detectors and descriptors are key low-level vision tools that many higher-level tasks build on.
no code implementations • CVPR 2017 • Donald G. Dansereau, Glenn Schuster, Joseph Ford, Gordon Wetzstein
Finally, we describe a processing toolchain, including a convenient spherical LF parameterization, and demonstrate depth estimation and post-capture refocus for indoor and outdoor panoramas with 15 x 15 x 1600 x 200 pixels (72 MPix) and a 138-degree FOV.
no code implementations • 16 Dec 2016 • Dorian Tsai, Donald G. Dansereau, Steve Martin, Peter Corke
This paper proposes the design of a custom mirror-based light field camera adapter that is cheap, simple in construction, and accessible.
no code implementations • 14 Jun 2016 • Donald G. Dansereau, Anders Eriksson, Jürgen Leitner
The method deals correctly with blur caused by 6-degree-of-freedom camera motion in complex 3-D scenes, without performing depth estimation.
no code implementations • CVPR 2013 • Donald G. Dansereau, Oscar Pizarro, Stefan B. Williams
Results include calibration of a commercially available camera using three calibration grid sizes over five datasets.