578 citations · 2.5k across the 216 of their papers we have counts for
26 papers · 2 filters
Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation
Haowen Deng, Mai Bui, Nassir Navab +3
In this work, we introduce Deep Bingham Networks (DBN), a generic framework that can naturally handle pose-related uncertainties and ambiguities arising in almost all real life app…
Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration
Mahdi Saleh, Shervin Dehghani, Benjamin Busam +2
3D Point clouds are a rich source of information that enjoy growing popularity in the vision community. However, due to the sparsity of their representation, learning models based…
Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds
Stefano Gasperini, Mohammad-Ali Nikouei Mahani, Alvaro Marcos-Ramiro +2
Panoptic segmentation has recently unified semantic and instance segmentation, previously addressed separately, thus taking a step further towards creating more comprehensive and e…
SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion
Shun-Cheng Wu, Keisuke Tateno, Nassir Navab +1
Real-time scene reconstruction from depth data inevitably suffers from occlusion, thus leading to incomplete 3D models. Partial reconstructions, in turn, limit the performance of a…
Polyp-artifact relationship analysis using graph inductive learned representations
Roger D. Soberanis-Mukul, Shadi Albarqouni, Nassir Navab
The diagnosis process of colorectal cancer mainly focuses on the localization and characterization of abnormal growths in the colon tissue known as polyps. Despite recent advances…
I Like to Move It: 6D Pose Estimation as an Action Decision Process
Benjamin Busam, Hyun Jun Jung, Nassir Navab
Object pose estimation is an integral part of robot vision and AR. Previous 6D pose retrieval pipelines treat the problem either as a regression task or discretize the pose space t…
SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification
Yida Wang, David Joseph Tan, Nassir Navab +1
Point clouds are often the default choice for many applications as they exhibit more flexibility and efficiency than volumetric data. Nevertheless, their unorganized nature -- poin…
A Learning-based Method for Online Adjustment of C-arm Cone-Beam CT Source Trajectories for Artifact Avoidance
Mareike Thies, Jan-Nico Zäch, Cong Gao +4
During spinal fusion surgery, screws are placed close to critical nerves suggesting the need for highly accurate screw placement. Verifying screw placement on high-quality tomograp…
Continual Class Incremental Learning for CT Thoracic Segmentation
Abdelrahman Elskhawy, Aneta Lisowska, Matthias Keicher +3
Deep learning organ segmentation approaches require large amounts of annotated training data, which is limited in supply due to reasons of confidentiality and the time required for…
DynaMiTe: A Dynamic Local Motion Model with Temporal Constraints for Robust Real-Time Feature Matching
Patrick Ruhkamp, Ruiqi Gong, Nassir Navab +1
Feature based visual odometry and SLAM methods require accurate and fast correspondence matching between consecutive image frames for precise camera pose estimation in real-time. C…
Attention based Multiple Instance Learning for Classification of Blood Cell Disorders
Ario Sadafi, Asya Makhro, Anna Bogdanova +4
Red blood cells are highly deformable and present in various shapes. In blood cell disorders, only a subset of all cells is morphologically altered and relevant for the diagnosis.…
Towards Unsupervised Learning for Instrument Segmentation in Robotic Surgery with Cycle-Consistent Adversarial Networks
Daniil Pakhomov, Wei Shen, Nassir Navab
Surgical tool segmentation in endoscopic images is an important problem: it is a crucial step towards full instrument pose estimation and it is used for integration of pre- and int…
Searching for Efficient Architecture for Instrument Segmentation in Robotic Surgery
Daniil Pakhomov, Nassir Navab
Segmentation of surgical instruments is an important problem in robot-assisted surgery: it is a crucial step towards full instrument pose estimation and is directly used for maskin…
Curriculum learning for improved femur fracture classification: scheduling data with prior knowledge and uncertainty
Amelia Jiménez-Sánchez, Diana Mateus, Sonja Kirchhoff +5
An adequate classification of proximal femur fractures from X-ray images is crucial for the treatment choice and the patients' clinical outcome. We rely on the commonly used AO sys…
Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation
Hong Joo Lee, Seong Tae Kim, Hakmin Lee +2
Recent studies have shown that ensemble approaches could not only improve accuracy and but also estimate model uncertainty in deep learning. However, it requires a large number of…
Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions
Johanna Wald, Helisa Dhamo, Nassir Navab +1
Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. Wit…
Semantic Image Manipulation Using Scene Graphs
Helisa Dhamo, Azade Farshad, Iro Laina +4
Image manipulation can be considered a special case of image generation where the image to be produced is a modification of an existing image. Image generation and manipulation hav…
Confident Coreset for Active Learning in Medical Image Analysis
Seong Tae Kim, Farrukh Mushtaq, Nassir Navab
Recent advances in deep learning have resulted in great successes in various applications. Although semi-supervised or unsupervised learning methods have been widely investigated,…
Self6D: Self-Supervised Monocular 6D Object Pose Estimation
Gu Wang, Fabian Manhardt, Jianzhun Shao +3
6D object pose estimation is a fundamental problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estima…
6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference
Mai Bui, Tolga Birdal, Haowen Deng +4
We present a multimodal camera relocalization framework that captures ambiguities and uncertainties with continuous mixture models defined on the manifold of camera poses. In highl…
Medical-based Deep Curriculum Learning for Improved Fracture Classification
Amelia Jiménez-Sánchez, Diana Mateus, Sonja Kirchhoff +5
Current deep-learning based methods do not easily integrate to clinical protocols, neither take full advantage of medical knowledge. In this work, we propose and compare several st…
Spatiotemporal-Aware Augmented Reality: Redefining HCI in Image-Guided Therapy
Javad Fotouhi, Arian Mehrfard, Tianyu Song +5
Suboptimal interaction with patient data and challenges in mastering 3D anatomy based on ill-posed 2D interventional images are essential concerns in image-guided therapies. Augmen…
ROAM: Random Layer Mixup for Semi-Supervised Learning in Medical Imaging
Tariq Bdair, Benedikt Wiestler, Nassir Navab +1
Medical image segmentation is one of the major challenges addressed by machine learning methods. Yet, deep learning methods profoundly depend on a large amount of annotated data, w…
CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning
Fabian Manhardt, Gu Wang, Benjamin Busam +5
Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances. This naturally hampers possible applications as, for instance, robots seamlessly…