no code implementations • 28 Jan 2024 • Sharib Ali, Yamid Espinel, Yueming Jin, Peng Liu, Bianca Güttner, Xukun Zhang, Lihua Zhang, Tom Dowrick, Matthew J. Clarkson, Shiting Xiao, Yifan Wu, Yijun Yang, Lei Zhu, Dai Sun, Lan Li, Micha Pfeiffer, Shahid Farid, Lena Maier-Hein, Emmanuel Buc, Adrien Bartoli
A total of 6 teams from 4 countries participated, whose proposed methods were evaluated on 16 images and two preoperative 3D models from two patients.
no code implementations • 30 Nov 2023 • Karim Makki, Adrien Bartoli
Specularities are numerous in endoscopic images.
no code implementations • 14 Mar 2023 • Yogesh Langhe, Katrin Skerl, Adrien Bartoli
The aim of this work is to implement a simple freehand ultrasound (US) probe calibration technique.
1 code implementation • 10 Jan 2023 • Mohammadreza Shetab-Bushehri, Miguel Aranda, Youcef Mezouar, Adrien Bartoli, Erol Ozgur
Tracking the 3D shape of a deforming object using only monocular 2D vision is a challenging problem.
no code implementations • 29 Nov 2022 • Agniva Sengupta, Adrien Bartoli
Extensible objects form a challenging case for NRSfM, owing to the lack of a sufficiently constrained extensible model of the point-cloud.
no code implementations • 10 Nov 2022 • Karim Makki, Adrien Bartoli
We show that these ellipses can be detected and used to estimate the plane's normal direction, forming a normal reconstruction method, which we validate on simulated data.
1 code implementation • 29 Jun 2022 • Fang Bai, Adrien Bartoli
We show that this property fortunately holds true for most common transformation models, including the affine and TPS models.
1 code implementation • CVPR 2022 • Fang Bai, Agniva Sengupta, Adrien Bartoli
To this end, we propose a novel mathematical abstraction for RS cameras observing a planar scene, called the scanline-homography, a 3x2 matrix with 5 DOFs.
no code implementations • 20 Aug 2021 • Alexandre Morgand, Mohamed Tamaazousti, Adrien Bartoli
Specularity prediction using our new model is tested against the most recent JOLIMAS version on both synthetic and real sequences with objects of various general shapes.
no code implementations • 9 Oct 2020 • Shaifali Parashar, Adrien Bartoli, Daniel Pizarro
Step 1 computes the optical flow from correspondences, step 2 reconstructs each 3D point's normal vector using multiple reference images and integrates them to form surfaces with the best reference and step 3 rejects the 3D points that break isometry in their local neighborhood.
1 code implementation • 20 Aug 2019 • Jose Lamarca, Shaifali Parashar, Adrien Bartoli, J. M. M. Montiel
In our experiments, DefSLAM processes close-up sequences of deforming scenes, both in a laboratory controlled experiment and in medical endoscopy sequences, producing accurate 3D models of the scene with respect to the moving camera.
no code implementations • 9 Apr 2019 • Bruno Ferrarini, Shoaib Ehsan, Adrien Bartoli, Aleš Leonardis, Klaus D. McDonald-Maier
This paper aims to fill this gap and proposes two experimental scenarios to assess the tolerance to imbalanced training data and to determine the generalization performance of a model with unfamiliar affine transformations of the images.
no code implementations • 4 Apr 2019 • John Lin, Mohamed El Amine Seddik, Mohamed Tamaazousti, Youssef Tamaazousti, Adrien Bartoli
We propose a novel learning approach, in the form of a fully-convolutional neural network (CNN), which automatically and consistently removes specular highlights from a single image by generating its diffuse component.
no code implementations • 19 Nov 2018 • David Fuentes-Jimenez, David Casillas-Perez, Daniel Pizarro, Toby Collins, Adrien Bartoli
Compared to previous non-DNN SfT methods, it does not involve numerical optimization at run-time, and is a dense, wide-baseline solution that does not demand, and does not suffer from, feature-based matching.
no code implementations • ECCV 2018 • Shaifali Parashar, Adrien Bartoli, Daniel Pizarro
We present self-calibrating isometric non-rigid structure- from-motion (SCIso-NRSfM), the first method to reconstruct a non-rigid object from at least three monocular images with constant but unknown focal length.
no code implementations • ECCV 2018 • Yizhen Lao, Omar Ait-Aider, Adrien Bartoli
Once the virtual deformations have been recovered using SfT, the camera pose and ego-motion are computed by registering the deformed scene on the original template.
no code implementations • 7 Jun 2018 • Shrinivasan Sankar, Adrien Bartoli
By generating sufficient images with known imaging conditions, we study to what extent CNNs can cope with hard imaging conditions for instance-level recognition in an active learning regime.
no code implementations • 11 Oct 2017 • David Casillas-Perez, Daniel Pizarro, Manuel Mazo, Adrien Bartoli
It is an important problem as it does not need initial conditions to obtain the unique solution and its the frequent solution that practical algorithms of the state-of-the-art give.
no code implementations • ICCV 2017 • Mathias Gallardo, Toby Collins, Adrien Bartoli
Significant progress has been recently made in Non-Rigid Structure-from-Motion (NRSfM).
no code implementations • CVPR 2016 • Shaifali Parashar, Daniel Pizarro, Adrien Bartoli
We study Isometric Non-Rigid Shape-from-Motion (Iso-NRSfM): given multiple intrinsically calibrated monocular images, we want to reconstruct the time-varying 3D shape of an object undergoing isometric deformations.
no code implementations • CVPR 2016 • Ajad Chhatkuli, Daniel Pizarro, Toby Collins, Adrien Bartoli
We show for the first time how to construct a Second-Order Cone Programming (SOCP) problem for Non-Rigid Shape-from-Motion (NRSfM) using the Maximum-Depth Heuristic (MDH).
no code implementations • ICCV 2015 • Shaifali Parashar, Daniel Pizarro, Adrien Bartoli, Toby Collins
Volumetric SfT uses the object's full volume to express the deformation constraints and reconstructs the object's surface and interior deformation.
no code implementations • CVPR 2015 • Mathias Gallardo, Daniel Pizarro, Adrien Bartoli, Toby Collins
We focus on isometric deformations, for which 2DSfT is a well-posed problem, and admits an analytical local solution which may be used to initialize nonconvex refinement.
no code implementations • CVPR 2015 • Abed Malti, Adrien Bartoli, Richard Hartley
We cast SfT (Shape-from-Template) as the search of a vector field (X, dX), composed of the pose X and the displacement dX that produces the deformation.
no code implementations • CVPR 2014 • Ajad Chhatkuli, Daniel Pizarro, Adrien Bartoli
It has been recently shown that reconstructing an isometric surface from a single 2D input image matched to a 3D template was a well-posed problem.
no code implementations • CVPR 2013 • Adrien Bartoli, Toby Collins
We propose (i) a general variational framework that applies to (calibrated and uncalibrated) general camera models and (ii) self-calibrating 3D reconstruction algorithms for the weak-perspective and full-perspective camera models.
no code implementations • CVPR 2013 • Abed Malti, Richard Hartley, Adrien Bartoli, Jae-Hak Kim
We extend the method of isometric surface reconstruction and more recent work on conformal surface reconstruction.