Deeper Depth Prediction with Fully Convolutional Residual Networks
- Iro Laina, C. Rupprecht, Vasileios Belagiannis, Federico Tombari, Nassir Navab
- Computer ScienceInternational Conference on 3D Vision
- 1 June 2016
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.
Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes
- Stefan Hinterstoißer, V. Lepetit, Nassir Navab
- Computer ScienceAsian Conference on Computer Vision
- 5 November 2012
A framework for automatic modeling, detection, and tracking of 3D objects with a Kinect and shows how to build the templates automatically from 3D models, and how to estimate the 6 degrees-of-freedom pose accurately and in real-time.
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
- Wadim Kehl, Fabian Manhardt, Federico Tombari, Slobodan Ilic, Nassir Navab
- Computer ScienceIEEE International Conference on Computer Vision
- 1 October 2017
A novel method for detecting 3D model instances and estimating their 6D poses from RGB data in a single shot that competes or surpasses current state-of-the-art methods that leverage RGBD data on multiple challenging datasets.
Model globally, match locally: Efficient and robust 3D object recognition
- Bertram Drost, M. Ulrich, Nassir Navab, Slobodan Ilic
- Computer ScienceIEEE Computer Society Conference on Computer…
- 13 June 2010
A novel method is proposed that creates a global model description based on oriented point pair features and matches that model locally using a fast voting scheme, which allows using much sparser object and scene point clouds, resulting in very fast performance.
Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes
This work presents a method for detecting 3D objects using multi-modalities based on an efficient representation of templates that capture the different modalities, and shows in many experiments on commodity hardware that it significantly outperforms state-of-the-art methods on single modalities.
Gradient Response Maps for Real-Time Detection of Textureless Objects
- Stefan Hinterstoißer, Cedric Cagniart, V. Lepetit
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 May 2012
A method for real-time 3D object instance detection that does not require a time-consuming training stage, and can handle untextured objects, and is much faster and more robust with respect to background clutter than current state-of-the-art methods is presented.
Tissue Classification as a Potential Approach for Attenuation Correction in Whole-Body PET/MRI: Evaluation with PET/CT Data
- A. Martinez-Möller, M. Souvatzoglou, S. Nekolla
- Medicine, PhysicsJournal of Nuclear Medicine
- 16 March 2009
A segmented attenuation map with 4 classes derived from CT data had only a small effect on the SUVs of 18F-FDG–avid lesions and did not change the interpretation for any patient, and appears to be practical and valid for MRI-based AC.
Dense image registration through MRFs and efficient linear programming
3D Pictorial Structures for Multiple Human Pose Estimation
- Vasileios Belagiannis, S. Amin, M. Andriluka, B. Schiele, Nassir Navab, Slobodan Ilic
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 1 June 2014
A novel 3D pictorial structures (3DPS) model is introduced that infers 3D human body configurations from the authors' reduced state space and is generic and applicable to both single and multiple human pose estimation.
Structure-Preserving Color Normalization and Sparse Stain Separation for Histological Images
Stain density correlation with ground truth and preference by pathologists were higher for images normalized using the method when compared to other alternatives, and a computationally faster extension of this technique is proposed for large whole-slide images that selects an appropriate patch sample instead of using the entire image to compute the stain color basis.