I
Iro Laina
Researcher at University of Oxford
Publications - 35
Citations - 4190
Iro Laina is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & Pose. The author has an hindex of 14, co-authored 25 publications receiving 3074 citations. Previous affiliations of Iro Laina include Technische Universität München.
Papers
More filters
Proceedings ArticleDOI
Deeper Depth Prediction with Fully Convolutional Residual Networks
TL;DR: A fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and depth maps is proposed and a novel way to efficiently learn feature map up-sampling within the network is presented.
Posted Content
Deeper Depth Prediction with Fully Convolutional Residual Networks
TL;DR: In this article, a fully convolutional architecture, encompassing residual learning, is proposed to model the ambiguous mapping between monocular images and depth maps, which can be trained end-to-end and does not rely on post-processing techniques such as CRFs or other additional refinement steps.
Proceedings ArticleDOI
CNN-SLAM: Real-Time Dense Monocular SLAM with Learned Depth Prediction
TL;DR: A method where CNN-predicted dense depth maps are naturally fused together with depth measurements obtained from direct monocular SLAM, based on a scheme that privileges depth prediction in image locations where monocularSLAM approaches tend to fail, e.g. along low-textured regions, and vice-versa.
Proceedings ArticleDOI
Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
TL;DR: This work proposes a frame-work for reformulating existing single-prediction models as multiple hypothesis prediction (MHP) models and an associated meta loss and optimization procedure to train them, and finds that MHP models outperform their single-hypothesis counterparts in all cases and expose valuable insights into the variability of predictions.
Book ChapterDOI
Concurrent Segmentation and Localization for Tracking of Surgical Instruments
Iro Laina,Nicola Rieke,Christian Rupprecht,Christian Rupprecht,Josué Page Vizcaíno,Abouzar Eslami,Federico Tombari,Nassir Navab,Nassir Navab +8 more
TL;DR: A novel method is proposed that takes advantage of the interdependency between localization and segmentation of the surgical tool and reformulate the 2D pose estimation as a heatmap regression and thereby enable a robust, concurrent regression of both tasks via deep learning.