Search Results for author: Mehmet Aygün

Found 6 papers, 1 papers with code

Exploiting Convolution Filter Patterns for Transfer Learning

no code implementations23 Aug 2017 Mehmet Aygün, Yusuf Aytar, Hazim Kemal Ekenel

In this paper, we introduce a new regularization technique for transfer learning.

Transfer Learning

Multi Modal Convolutional Neural Networks for Brain Tumor Segmentation

no code implementations17 Sep 2018 Mehmet Aygün, Yusuf Hüseyin Şahin, Gözde Ünal

In this work, we propose a multi-modal Convolutional Neural Network (CNN) approach for brain tumor segmentation.

Brain Tumor Segmentation Segmentation +2

Unsupervised Dense Shape Correspondence using Heat Kernels

no code implementations23 Oct 2020 Mehmet Aygün, Zorah Lähner, Daniel Cremers

In this work, we propose an unsupervised method for learning dense correspondences between shapes using a recent deep functional map framework.

4D Panoptic LiDAR Segmentation

1 code implementation CVPR 2021 Mehmet Aygün, Aljoša Ošep, Mark Weber, Maxim Maximov, Cyrill Stachniss, Jens Behley, Laura Leal-Taixé

In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points.

4D Panoptic Segmentation Benchmarking +4

Demystifying Unsupervised Semantic Correspondence Estimation

no code implementations11 Jul 2022 Mehmet Aygün, Oisin Mac Aodha

We explore semantic correspondence estimation through the lens of unsupervised learning.

Semantic correspondence

SAOR: Single-View Articulated Object Reconstruction

no code implementations23 Mar 2023 Mehmet Aygün, Oisin Mac Aodha

We introduce SAOR, a novel approach for estimating the 3D shape, texture, and viewpoint of an articulated object from a single image captured in the wild.

Object Object Reconstruction

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