Displets: Resolving stereo ambiguities using object knowledge

Güney, Fatma; Geiger, Andreas

doi:10.1109/cvpr.2015.7299044

Cited by 182 publications

(91 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each class then has associated weightings favouring different types of reconstruction. Very recently, Guney and Geiger [11] have forgone this weighting procedure, instead using detection of cars in driving footage to transfer 3D car models into the reconstruction.…”

Section: Joint Approachesmentioning

confidence: 99%

Exploiting High Level Scene Cues in Stereo Reconstruction

Hadfield

Bowden

2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We present a novel approach to 3D reconstruction which is inspired by the human visual system. This system unifies standard appearance matching and triangulation techniques with higher level reasoning and scene understanding, in order to resolve ambiguities between different interpretations of the scene. The types of reasoning integrated in the approach includes recognising common configurations of surface normals and semantic edges (e.g. convex, concave and occlusion boundaries). We also recognise the coplanar, collinear and symmetric structures which are especially common in man made environments.

show abstract

Section: Joint Approachesmentioning

confidence: 99%

Exploiting High Level Scene Cues in Stereo Reconstruction

Hadfield

Bowden

2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…Using HOG features, they adapt the mean shape to a newly observed instance of the object by registering the anchor points. (Güney and Geiger, 2015) leverage semantic information to sample CAD shapes with an application to binocular stereo matching. (Dame et al, 2013) use an object detector to infer the initial pose and shape parameters for an object model which they then optimize in a variational SLAM framework.…”

Section: Related Workmentioning

confidence: 99%

Joint 3d Estimation of Vehicles and Scene Flow

Menze

Heipke

Geiger

2015

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

323

215

View full text Add to dashboard Cite

ABSTRACT:Three-dimensional reconstruction of dynamic scenes is an important prerequisite for applications like mobile robotics or autonomous driving. While much progress has been made in recent years, imaging conditions in natural outdoor environments are still very challenging for current reconstruction and recognition methods. In this paper, we propose a novel unified approach which reasons jointly about 3D scene flow as well as the pose, shape and motion of vehicles in the scene. Towards this goal, we incorporate a deformable CAD model into a slanted-plane conditional random field for scene flow estimation and enforce shape consistency between the rendered 3D models and the parameters of all superpixels in the image. The association of superpixels to objects is established by an index variable which implicitly enables model selection. We evaluate our approach on the challenging KITTI scene flow dataset in terms of object and scene flow estimation. Our results provide a prove of concept and demonstrate the usefulness of our method.

show abstract

“…However they required the background reconstruction to already be completed in order to constrain the placement of the car models. More recently Guney and Geiger [48] proposed a technique where the 3D car models were inserted before background reconstruction took place (i.e. the recognition constrained the reconstruction).…”

Section: Joint Approachesmentioning

confidence: 99%