no code implementations • 25 Apr 2024 • Leandro Di Bella, Yangxintong Lyu, Adrian Munteanu
This paper presents DeepKalPose, a novel approach for enhancing temporal consistency in monocular vehicle pose estimation applied on video through a deep-learning-based Kalman Filter.
no code implementations • 10 Apr 2024 • Remco Royen, Adrian Munteanu
To the best of our knowledge, the proposed method is the first to propose a resolution-scalable approach for 3D semantic segmentation of point clouds based on deep learning.
1 code implementation • 19 Jun 2023 • Ioannis Romanelis, Vlassis Fotis, Konstantinos Moustakas, Adrian Munteanu
In this paper we delve into the properties of transformers, attained through self-supervision, in the point cloud domain.
Ranked #13 on 3D Point Cloud Classification on ScanObjectNN (OBJ-ONLY (OA) metric, using extra training data)
3D Point Cloud Classification Explainable artificial intelligence
no code implementations • 28 Apr 2021 • Pengpeng Hu, Edmond S. L Ho, Adrian Munteanu
As easy-to-use as taking a photo using a mobile phone, our algorithm only needs two depth images of the front-facing and back-facing bodies.
no code implementations • 15 Mar 2021 • Pengpeng Hu, Adrian Munteanu
In this letter, to the best of knowledge, the first method for the registration of 3D shapes without overlap, assuming that the shapes correspond to partial views of a known semi-rigid 3D prior is presented.
no code implementations • 20 Jan 2021 • Remco Royen, Leon Denis, Quentin Bolsee, Pengpeng Hu, Adrian Munteanu
To the best of our knowledge, this is the first work presenting a generic solution able to achieve quality scalable results within the deep learning framework.
no code implementations • 28 Aug 2020 • Tien Huu Do, Duc Minh Nguyen, Giannis Bekoulis, Adrian Munteanu, Nikos Deligiannis
Among the existing GCNNs, many methods can be viewed as instances of a neural message passing motif; features of nodes are passed around their neighbors, aggregated and transformed to produce better nodes' representations.
no code implementations • 13 Aug 2020 • Pengpeng Hu, Nastaran Nourbakhsh Kaashki, Vasile Dadarlat, Adrian Munteanu
In this paper, we propose the first learning-based approach to estimate the human body shape under clothing from a single dressed-human scan, dubbed Body PointNet.
no code implementations • 30 Apr 2020 • Boris Joukovsky, Pengpeng Hu, Adrian Munteanu
In this Letter, the authors propose a deep learning based method to perform semantic segmentation of clothes from RGB-D images of people.
no code implementations • 24 Mar 2020 • Pengpeng Hu, Nastaran Nourbakhsh, Jing Tian, Stephan Sturges, Vasile Dadarlat, Adrian Munteanu
In this paper, we present the first general method for virtual try-ons that is fully automatic and suitable for many items including garments, hair, shoes, watches, necklaces, hats, and so on.