Search Results for author: Eren Erdal Aksoy

Found 15 papers, 9 papers with code

Semantics-aware LiDAR-Only Pseudo Point Cloud Generation for 3D Object Detection

no code implementations16 Sep 2023 Tiago Cortinhal, Idriss Gouigah, Eren Erdal Aksoy

Although LiDAR sensors are crucial for autonomous systems due to providing precise depth information, they struggle with capturing fine object details, especially at a distance, due to sparse and non-uniform data.

3D Object Detection Object +2

Depth- and Semantics-aware Multi-modal Domain Translation: Generating 3D Panoramic Color Images from LiDAR Point Clouds

1 code implementation15 Feb 2023 Tiago Cortinhal, Eren Erdal Aksoy

This work presents a new depth- and semantics-aware conditional generative model, named TITAN-Next, for cross-domain image-to-image translation in a multi-modal setup between LiDAR and camera sensors.

Autonomous Vehicles Image-to-Image Translation

FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping

1 code implementation19 Oct 2022 Felix Rosberg, Eren Erdal Aksoy, Fernando Alonso-Fernandez, Cristofer Englund

In this work, we present a new single-stage method for subject agnostic face swapping and identity transfer, named FaceDancer.

Attribute Decoder +2

Semantic State Estimation in Cloth Manipulation Tasks

1 code implementation22 Mar 2022 Georgies Tzelepis, Eren Erdal Aksoy, Júlia Borràs, Guillem Alenyà

Understanding of deformable object manipulations such as textiles is a challenge due to the complexity and high dimensionality of the problem.

A Variational Graph Autoencoder for Manipulation Action Recognition and Prediction

1 code implementation25 Oct 2021 Gamze Akyol, Sanem Sariel, Eren Erdal Aksoy

The input of the proposed network is a set of semantic graphs which store the spatial relations between subjects and objects in the scene.

Action Recognition

MOHAQ: Multi-Objective Hardware-Aware Quantization of Recurrent Neural Networks

no code implementations2 Aug 2021 Nesma M. Rezk, Tomas Nordström, Dimitrios Stathis, Zain Ul-Abdin, Eren Erdal Aksoy, Ahmed Hemani

On SiLago, we found solutions that achieve 97\% and 86\% of the maximum possible speedup and energy saving, with a minor increase in error.

Quantization speech-recognition +1

AI perspectives in Smart Cities and Communities to enable road vehicle automation and smart traffic control

no code implementations7 Apr 2021 Cristofer Englund, Eren Erdal Aksoy, Fernando Alonso-Fernandez, Martin Daniel Cooney, Sepideh Pashami, Bjorn Astrand

This paper describes AI perspectives in SCC and gives an overview of AI-based technologies used in traffic to enable road vehicle automation and smart traffic control.

SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Driving

3 code implementations18 Sep 2019 Eren Erdal Aksoy, Saimir Baci, Selcuk Cavdar

SalsaNet segments the road, i. e. drivable free-space, and vehicles in the scene by employing the Bird-Eye-View (BEV) image projection of the point cloud.

3D Semantic Segmentation Autonomous Driving +2

Introducing the Simulated Flying Shapes and Simulated Planar Manipulator Datasets

2 code implementations2 Jul 2018 Fabio Ferreira, Jonas Rothfuss, Eren Erdal Aksoy, You Zhou, Tamim Asfour

We release two artificial datasets, Simulated Flying Shapes and Simulated Planar Manipulator that allow to test the learning ability of video processing systems.

Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution

1 code implementation12 Jan 2018 Jonas Rothfuss, Fabio Ferreira, Eren Erdal Aksoy, You Zhou, Tamim Asfour

We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experiences.

Retrieval

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