Search Results for author: Angel Martínez-González

Found 6 papers, 3 papers with code

An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning

1 code implementation2 Aug 2021 Marco Ewerton, Angel Martínez-González, Jean-Marc Odobez

In this paper, we propose to frame the learning of pushing policies (where to push and how) by DQNs as an image-to-image translation problem and exploit an Hourglass-based architecture.

Image-to-Image Translation Translation

Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation

1 code implementation10 Nov 2020 Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez

We propose to leverage recent advances in reliable 2D pose estimation with Convolutional Neural Networks (CNN) to estimate the 3D pose of people from depth images in multi-person Human-Robot Interaction (HRI) scenarios.

2D Pose Estimation 3D Human Pose Estimation +1

Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation

no code implementations2 Dec 2019 Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez

i) we study several CNN architecture designs combining pose machines relying on the cascade of detectors concept with lightweight and efficient CNN structures; ii) to address the need for large training datasets with high variability, we rely on semi-synthetic data combining multi-person synthetic depth data with real sensor backgrounds; iii) we explore domain adaptation techniques to address the performance gap introduced by testing on real depth images; iv) to increase the accuracy of our fast lightweight CNN models, we investigate knowledge distillation at several architecture levels which effectively enhance performance.

2D Pose Estimation Domain Adaptation +2

Real-time Convolutional Networks for Depth-based Human Pose Estimation

no code implementations30 Oct 2019 Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez

(i) we propose a fast and efficient network based on residual blocks (called RPM) for body landmark localization from depth images; (ii) we created a public dataset DIH comprising more than 170k synthetic images of human bodies with various shapes and viewpoints as well as real (annotated) data for evaluation; (iii) we show that our model trained on synthetic data from scratch can perform well on real data, obtaining similar results to larger models initialized with pre-trained networks.

Human Detection Multi-Person Pose Estimation

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