2 code implementations • 9 Apr 2024 • Raphael Sulzer, Florent Lafarge
We introduce two key novelties that enable the construction of plane arrangements for complex objects and entire scenes: an ordering scheme for the plane insertion and the direct use of input points during arrangement construction.
no code implementations • 11 Jul 2023 • Johann Lussange, Mulin Yu, Yuliya Tarabalka, Florent Lafarge
We here propose a method for urban 3D reconstruction named KIBS(\textit{Keypoints Inference By Segmentation}), which comprises two novel features: i) a full deep learning approach for the 3D detection of the roof sections, and ii) only one single (non-orthogonal) satellite raster image as model input.
no code implementations • 8 Feb 2022 • Gaetan Bahl, Lionel Daniel, Florent Lafarge
While object detection methods traditionally make use of pixel-level masks or bounding boxes, alternative representations such as polygons or active contours have recently emerged.
no code implementations • CVPR 2022 • Mulin Yu, Florent Lafarge
We present an algorithm for detecting planar primitives from unorganized 3D point clouds.
no code implementations • 9 Dec 2021 • Gaetan Bahl, Mehdi Bahri, Florent Lafarge
By contrast, we propose a method that directly infers the final road graph in a single pass.
no code implementations • CVPR 2018 • Hao Fang, Florent Lafarge, Mathieu Desbrun
Interpreting 3D data such as point clouds or surface meshes depends heavily on the scale of observation.
no code implementations • CVPR 2018 • Jean-Philippe Bauchet, Florent Lafarge
Recent works showed that floating polygons can be an interesting alternative to traditional superpixels, especially for analyzing scenes with strong geometric signatures, as man-made environments.
no code implementations • CVPR 2015 • Jean-Dominique Favreau, Florent Lafarge, Adrien Bousseau
Many design tasks involve the creation of new objects in the context of an existing scene.
no code implementations • CVPR 2015 • Liuyun Duan, Florent Lafarge
The over-segmentation of images into atomic regions has become a standard and powerful tool in Vision.
no code implementations • CVPR 2013 • Dengfeng Chai, Wolfgang Forstner, Florent Lafarge
Our experiments on a variety of problems illustrate the potential of our approach in terms of accuracy, flexibility and efficiency.