A
Adrien Bartoli
Researcher at University of Auvergne
Publications - 309
Citations - 7882
Adrien Bartoli is an academic researcher from University of Auvergne. The author has contributed to research in topics: Image registration & Bundle adjustment. The author has an hindex of 37, co-authored 286 publications receiving 6635 citations. Previous affiliations of Adrien Bartoli include Commissariat à l'énergie atomique et aux énergies alternatives & French Institute for Research in Computer Science and Automation.
Papers
More filters
Proceedings ArticleDOI
Fast explicit diffusion for accelerated features in nonlinear scale spaces
TL;DR: A novel and fast multiscale feature detection and description approach that exploits the benefits of nonlinear scale spaces and introduces a Modified-Local Difference Binary (M-LDB) descriptor that is highly efficient, exploits gradient information from the non linear scale space, is scale and rotation invariant and has low storage requirements.
Book ChapterDOI
KAZE features
TL;DR: KAZE features, a novel multiscale 2D feature detection and description algorithm in nonlinear scale spaces, can make blurring locally adaptive to the image data, reducing noise but retaining object boundaries, obtaining superior localization accuracy and distinctiviness.
Journal ArticleDOI
Structure-from-motion using lines: representation, triangulation, and bundle adjustment
Adrien Bartoli,Peter Sturm +1 more
TL;DR: Results show that the triangulation algorithm outperforms standard linear and bias-corrected quasi-linear algorithms, and that bundle adjustment using the orthonormal representation yields results similar to the standard maximum likelihood trifocal tensor algorithm, while being usable for any number of views.
Journal ArticleDOI
Optical techniques for 3D surface reconstruction in computer-assisted laparoscopic surgery.
Lena Maier-Hein,Peter Mountney,Adrien Bartoli,Haytham Elhawary,Daniel S. Elson,Anja Groch,Andreas Kolb,Marcos A. Rodrigues,Jonathan M. Sorger,Stefanie Speidel,Danail Stoyanov +10 more
TL;DR: The state-of-the-art methods for optical intra-operative 3D reconstruction in laparoscopic surgery is reviewed and the technical challenges and future perspectives towards clinical translation are discussed.
Journal ArticleDOI
Monocular Template-based Reconstruction of Inextensible Surfaces
TL;DR: A monocular 3D reconstruction algorithm for inextensible deformable surfaces that uses point correspondences between a single image of the deformed surface taken by a camera with known intrinsic parameters and a template to recover the 3D surface shape as seen in the image.