6 accepted papers
"Object pose estimation is a crucial task in computer vision and augmented reality. One of its key challenges is the difficulty of annotation of real training data and the lack of textured CAD models. Therefore, pipelines which do not require CAD models and which can be trained with few labeled imag…
Applications like autonomous driving, surveillance, or any application that demands scene analysis requires object detection, semantic segmentation and instance segmentation. In this paper, we focus on the problem of detecting each instance of a specific category of objects, specifically persons. A…
We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior, (b) real observations of a scene can be incorporated while observing global consistency, (c) unobserved regions can be…
While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. Therefore, it has become common practice to use available synthetic samples along domain adaptation schemes to prep…
Deep convolutional neural networks (CNNs) have achieved tremendous success in image recognition tasks. However, the performance of CNNs degrade in situations where the input image is degraded by compression artifacts, blur or noise. In this paper, we analyze some of the common CNNs for degradations…
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. Inspired by the descriptor learning approach of Wohlhart et al. [1], we propose a method that introduces the dynamic margin…