121 citations · 240 across the 9 of their papers we have counts for
14 papers
Photo-realistic Neural Domain Randomization
Sergey Zakharov, Rares Ambrus, Vitor Guizilini +2
Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed…
Monocular Differentiable Rendering for Self-Supervised 3D Object Detection
Deniz Beker, Hiroharu Kato, Mihai Adrian Morariu +4
3D object detection from monocular images is an ill-posed problem due to the projective entanglement of depth and scale. To overcome this ambiguity, we present a novel self-supervi…
Differentiable Rendering: A Survey
Hiroharu Kato, Deniz Beker, Mihai Morariu +4
Deep neural networks (DNNs) have shown remarkable performance improvements on vision-related tasks such as object detection or image segmentation. Despite their success, they gener…
Real-Time 3D Model Tracking in Color and Depth on a Single CPU Core
Wadim Kehl, Federico Tombari, Slobodan Ilic +1
We present a novel method to track 3D models in color and depth data. To this end, we introduce approximations that accelerate the state-of-the-art in region-based tracking by an o…
Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors
Sergey Zakharov, Wadim Kehl, Arjun Bhargava +1
We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data. Our autolabeling method solves an…
3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin
Sergey Zakharov, Wadim Kehl, Benjamin Planche +2
In this paper, we address the problem of 3D object instance recognition and pose estimation of localized objects in cluttered environments using convolutional neural networks. Insp…
DeceptionNet: Network-Driven Domain Randomization
Sergey Zakharov, Wadim Kehl, Slobodan Ilic
We present a novel approach to tackle domain adaptation between synthetic and real data. Instead, of employing "blind" domain randomization, i.e., augmenting synthetic renderings w…
ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape
Fabian Manhardt, Wadim Kehl, Adrien Gaidon
We present a deep learning method for end-to-end monocular 3D object detection and metric shape retrieval. We propose a novel loss formulation by lifting 2D detection, orientation,…
Deep Model-Based 6D Pose Refinement in RGB
Fabian Manhardt, Wadim Kehl, Nassir Navab +1
We present a novel approach for model-based 6D pose refinement in color data. Building on the established idea of contour-based pose tracking, we teach a deep neural network to pre…
BOP: Benchmark for 6D Object Pose Estimation
Tomas Hodan, Frank Michel, Eric Brachmann +13
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image. The training data consists of a texture-mapped 3D object model or images of the obj…
SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again
Wadim Kehl, Fabian Manhardt, Federico Tombari +2
We present a novel method for detecting 3D model instances and estimating their 6D poses from RGB data in a single shot. To this end, we extend the popular SSD paradigm to cover th…
An Octree-Based Approach towards Efficient Variational Range Data Fusion
Wadim Kehl, Tobias Holl, Federico Tombari +2
Volume-based reconstruction is usually expensive both in terms of memory consumption and runtime. Especially for sparse geometric structures, volumetric representations produce a h…
Hashmod: A Hashing Method for Scalable 3D Object Detection
Wadim Kehl, Federico Tombari, Nassir Navab +2
We present a scalable method for detecting objects and estimating their 3D poses in RGB-D data. To this end, we rely on an efficient representation of object views and employ hashi…
Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation
Wadim Kehl, Fausto Milletari, Federico Tombari +2
We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting. For regression, we employ a convolutional auto-encoder…