activity
20172020
most citedGuided Anisotropic Diffusion and Iterative Learning for Weakly Supervised Change Detection

34 citations · 73 across the 5 of their papers we have counts for

collaborators

14 papers

cs.CV2020

Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study

Javiera Castillo-Navarro, Bertrand Le Saux, Alexandre Boulch +2

The development of semi-supervised learning techniques is essential to enhance the generalization capacities of machine learning algorithms. Indeed, raw image data are abundant whi…

cs.CV2020

FLOT: Scene Flow on Point Clouds Guided by Optimal Transport

Gilles Puy, Alexandre Boulch, Renaud Marlet

We propose and study a method called FLOT that estimates scene flow on point clouds. We start the design of FLOT by noticing that scene flow estimation on point clouds reduces to e…

cs.CV2020

STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation

Pierre Godet, Alexandre Boulch, Aurélien Plyer +1

We present a new lightweight CNN-based algorithm for multi-frame optical flow estimation. Our solution introduces a double recurrence over spatial scale and time through repeated u…

cs.CV2020

FKAConv: Feature-Kernel Alignment for Point Cloud Convolution

Alexandre Boulch, Gilles Puy, Renaud Marlet

Recent state-of-the-art methods for point cloud processing are based on the notion of point convolution, for which several approaches have been proposed. In this paper, inspired by…

cs.CV20191 cited

Technical Report: Co-learning of geometry and semantics for online 3D mapping

Marcela Carvalho, Maxime Ferrera, Alexandre Boulch +3

This paper is a technical report about our submission for the ECCV 2018 3DRMS Workshop Challenge on Semantic 3D Reconstruction \cite{Tylecek2018rms}. In this paper, we address 3D s…

cs.CV201919 cited

Surface Reconstruction from 3D Line Segments

Pierre-Alain Langlois, Alexandre Boulch, Renaud Marlet

In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We pr…