In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for
many-task vehicle analysis from a given image. A robust convolutional network is introduced …

While 3D object representations are being revived in the context of multi-view object class
detection and scene understanding, they have not yet attained wide-spread use in fine …

We present a method to infer 3D pose and shape of vehicles from a single image. To tackle
this ill-posed problem, we optimize two-scale projection consistency between the generated …

Current object class recognition systems typically target 2D bounding box localization,
encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the …

Geometric 3D reasoning at the level of objects has received renewed attention recently in
the context of visual scene understanding. The level of geometric detail, however, is typically …

Monocular 3D object detection is well-known to be a challenging vision task due to the loss
of depth information; attempts to recover depth using separate image-only approaches lead …

We present an approach to detecting and analyzing the 3D configuration of objects in real-
world images with heavy occlusion and clutter. We focus on the application of finding and …

As objects are inherently 3-dimensional, they have been modeled in 3D in the early days of
computer vision. Due to the ambiguities arising from mapping 2D features to 3D models, 2D …

As objects are inherently 3D, they have been modeled in 3D in the early days of computer
vision. Due to the ambiguities arising from mapping 2D features to 3D models, 3D object …

Basic-level object category recognition has made remarkable progress over the last decade,
both in image-level categorization and bounding box localization settings [3]. More recently …