Iro Laina

News

• I have joined the Visual Geometry Group at the University of Oxford (Feb 2020).
• One paper accepted at ICCV 2019.
• Outstanding reviewer CVPR 2019.
• One paper accepted at ACCV 2018.
• One paper accepted at CVPR 2018 as a spotlight presentation
• Our FCRN method on surgical tool segmentation won 3rd place on the EndoVis Robotic Instrument Segmentation Challenge 2017! (1st place on multi-class segmentation, 3rd overall)
• Best presentation award at the International Computer Vision Summer School (ICVSS 2017)
• One paper accepted at ICCV 2017
• One paper accepted at MICCAI 2017
• One paper accepted at CVPR 2017

Teaching

• Hauptseminar Deep Generative Models (2018WiSe)
• Hauptseminar Recent Trends in 3D Computer Vision and Deep Learning (2018WiSe)
• Praktikum Perception and Learning in Robotics and Augmented Reality (2018SoSe)
• Hauptseminar Deep Generative Models (2018SoSe)
• Hauptseminar Deep Generative Models (2017WiSe)
• Hauptseminar Recent Trends in 3D Computer Vision and Deep Learning (2017WiSe)
• Praktikum Perception and Learning in Robotics and Augmented Reality (2017SoSe)
• Hauptseminar Recent Trends in 3D Computer Vision (2016WiSe)
• Hauptseminar Foundations of Computer Vision (2016WiSe)

Publications

2020
	H. Dhamo, A. Farshad, I. Laina, N. Navab, G. D. Hager, F. Tombari, C. Rupprecht Semantic Image Manipulation Using Scene Graphs IEEE Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, June 2020 The first two authors contributed equally. (bib)
2019
	I. Laina, N. Navab, C. Rupprecht Towards Unsupervised Image Captioning with Shared Multimodal Embeddings International Conference on Computer Vision (ICCV), Seoul, Korea, October 2019. (bib)
	H. Dhamo, K. Tateno, I. Laina, N. Navab, F. Tombari Peeking Behind Objects: Layered Depth Prediction from a Single Image Pattern Recognition Letters, Vol. 125, 2019 (bib)
2018
	C. Rupprecht, I. Laina, N. Navab, G. D. Hager, F. Tombari Guide Me: Interacting with Deep Networks Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, June 2018. Spotlight. The first two authors contribute equally to this paper. (bib)
	G. Ghazaei, I. Laina, C. Rupprecht, F. Tombari, N. Navab, K. Nazarpour Dealing with Ambiguity in Robotic Grasping via Multiple Predictions Asian Conference on Computer Vision and Pattern Recognition (ACCV), Perth, Australia, December 2018. (bib)
2017
	C. Rupprecht, I. Laina, R. DiPietro, M. Baust, F. Tombari, N. Navab, G. D. Hager Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses International Conference on Computer Vision (ICCV 2017), Venice, Italy, October 2017 (bib)
	I. Laina, N. Rieke, C. Rupprecht, J. Page Vizcaino, A. Eslami, F. Tombari, N. Navab Concurrent Segmentation and Localization for Tracking of Surgical Instruments Accepted to Proceedings of the 20th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Quebec, Canada, September 2017. A pre-print version is available online at arXiv. The first two authors contribute equally to this paper. (bib)
	K. Tateno, F. Tombari, I. Laina, N. Navab CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, USA, June, 2017. The first two authors contribute equally to this paper. (bib)
2016
	I. Laina, C. Rupprecht, V. Belagiannis, F. Tombari, N. Navab Deeper Depth Prediction with Fully Convolutional Residual Networks International Conference on 3DVision (3DV), Stanford University, California, USA, October 2016. Oral presentation. The first two authors contribute equally to this paper. (bib)

Student Projects

Running

I will be not taking up on any more student projects.

Finished
Master Thesis	Explained Predictions for Neural Networks (Christian Rupprecht, Iro Laina, Federico Tombari, Prof. Nassir Navab)
DA/MA/BA	Weakly supervised semantic segmentation via multiple hypothesis prediction (Iro Laina, Christian Rupprecht, Federico Tombari, Nassir Navab)
Master Thesis	3D Bounding Box Prediction from RGB and LiDAR Data Using 2D Proposals (Iro Laina, Federico Tombari, Nassir Navab)
DA/MA/BA	Deep Learning for Depth Estimation from Single Images (Iro Laina, Dr. Federico Tombari, Prof. Nassir Navab)
DA/MA/BA	Depth Prediction from Structured Light using Fully Convolutional Neural Networks (Iro Laina, Keisuke Tateno, Federico Tombari, Prof. Nassir Navab)
DA/MA/BA	Adversarial Multiple Hypothesis Prediction (Christian Rupprecht, Iro Laina, Federico Tombari, Prof. Nassir Navab)
Master Thesis	Efficient Object Detection using Fully Convolutional Neural Networks (Iro Laina, Federico Tombari, Prof. Nassir Navab)
Master Thesis	Deep Intrinsic Image Decomposition (Christian Rupprecht, Iro Laina, Federico Tombari, Prof. Nassir Navab)

Research Projects

Depth Estimation from a single RGB Image

Kooperationsprojekt SFB 824 (3. Förderperiode) & BFS

The goal of the BFS Project: Immunoprofiling using Neural Networks (IPN2) is to develop a method based on recent advances in Deep Learning to allow characterization of a patient's tumor as ″hot″ or ″cold″ depending on the identified Immunoprofile. Recent research has shown that many tumors are infiltrated by immuno-competent cells and that the amount, type and location of the infiltrated lymph nodes in primary tumors provide valuable prognostic information. In contrast to a ″cold tumor″, a ″hot tumor″ is characterized by an active immune system which the tumor has identified as threat. This identification provides the basis for selecting the therapy best suitable for the individual patient.