Publications by Isinsu Katircioglu

STEEL-3dPointClouds: dataset supporting quantification of residual life and reusability of steel beam-columns

Dimitrios Lignos, Isinsu Katircioglu, Nenad Bijelic, Guillaume Romain Obozinski

This paper presents STEEL-3dPointClouds, a dataset of deformed steel beam-columns obtained using high-fidelity physics-based numerical simulations. These simulations trace the inelastic deformations of hot-rolled wide-flange steel beam-columns under differ ...

Springer Science and Business Media LLC2025

Encoder-Decoder Models for Human Segmentation and Motion Analysis

Isinsu Katircioglu

Detecting people from 2D images and analyzing their motion in 3D have been long standing computer vision problems central to numerous applications such as autonomous driving and athletic training. Recently, with the availability of large amounts of trainin ...

EPFL2022

3D Pose Based Feedback For Physical Exercises

Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Sena Kiciroglu, Ziqi Zhao, Hugues François Rémi Vinzant, Yuan Cheng, Ziyi Zhao

Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mistakes made by a user and proposes corrective measures for easier and safer ...

Springer2022

Self-supervised Segmentation via Background Inpainting

Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Helge Jochen Rhodin, Victor Constantin

While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this when annotating data is prohibitively e ...

2022

Human Detection and Segmentation via Multi-view Consensus

Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Helge Jochen Rhodin

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic activities and ...

IEEE2021

Neural Scene Decomposition for Multi-Person Motion Capture

Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Helge Jochen Rhodin, Victor Constantin

Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networks that were initially trained on ImageNet, mostly because the learned featu ...

IEEE2019

Learning Monocular 3D Human Pose Estimation from Multi-view Images

Pascal Fua, Mathieu Salzmann, Frédéric Meyer, Isinsu Katircioglu, Helge Jochen Rhodin, Victor Constantin

Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such database exists. Ma ...

IEEE2018

Structured Prediction of 3D Human Pose with Deep Neural Networks

Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Vincent Lepetit, Bugra Tekin

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these dependencies via a ...

2016