Search Results for author: Pablo F. Alcantarilla

Found 7 papers, 1 papers with code

SeMLaPS: Real-time Semantic Mapping with Latent Prior Networks and Quasi-Planar Segmentation

1 code implementation28 Jun 2023 Jingwen Wang, Juan Tarrio, Lourdes Agapito, Pablo F. Alcantarilla, Alexander Vakhitov

We present a new methodology for real-time semantic mapping from RGB-D sequences that combines a 2D neural network and a 3D network based on a SLAM system with 3D occupancy mapping.

Image Segmentation Semantic Segmentation

Towards Bounding-Box Free Panoptic Segmentation

no code implementations18 Feb 2020 Ujwal Bonde, Pablo F. Alcantarilla, Stefan Leutenegger

Our approach is distinct from previous works in panoptic segmentation that rely on a combination of a semantic segmentation network with a computationally costly instance segmentation network based on bounding box proposals, such as Mask R-CNN, to guide the prediction of instance labels using a Mixture-of-Expert (MoE) approach.

Instance Segmentation Panoptic Segmentation +1

Street-view change detection with deconvolutional networks

no code implementations Autonomous Robots 2018 Pablo F. Alcantarilla, Simon Stent, Germán Ros, Roberto Arroyo, Riccardo Gherardi

We propose a system for performing structural change detection in street-view videos captured by a vehicle-mounted monocular camera over time.

3D Reconstruction Change Detection +2

A Continuous Optimization Approach for Efficient and Accurate Scene Flow

no code implementations27 Jul 2016 Zhaoyang Lv, Chris Beall, Pablo F. Alcantarilla, Fuxin Li, Zsolt Kira, Frank Dellaert

We propose a continuous optimization method for solving dense 3D scene flow problems from stereo imagery.


Noise Models in Feature-based Stereo Visual Odometry

no code implementations1 Jul 2016 Pablo F. Alcantarilla, Oliver J. Woodford

Feature-based visual structure and motion reconstruction pipelines, common in visual odometry and large-scale reconstruction from photos, use the location of corresponding features in different images to determine the 3D structure of the scene, as well as the camera parameters associated with each image.

Visual Odometry

Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation

no code implementations6 Apr 2016 German Ros, Simon Stent, Pablo F. Alcantarilla, Tomoki Watanabe

In this work we investigate the problem of road scene semantic segmentation using Deconvolutional Networks (DNs).

Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.