Simultaneous Monocular 2D Segmentation, 3D Pose Recovery and 3D Reconstruction

65 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, neutral): “Sophisticated mathematical formulations have also been introduced to adapt 3D shape models to observations with diﬀerent degrees of supervision [27] and diﬀerent regularization strategies [28].”
Dense Reconstruction Using 3D Object Shape Priors (2013, methodology): “Here, in a manner similar to [19], we represent the shape-prior using GP-LVM and optimise an energy over the pose and a low-dimensional latent shape space.”
Joint 3d Estimation of Vehicles and Scene Flow (2015, methodology): “Recently, (Prisacariu et al., 2013) proposed an efficient way to compress prior information from CAD models with complex shape variations using Gaussian Process Latent Variable Models.”
Single image 3D object detection and pose estimation for grasping (2014, methodology): “For instance, Gaussian Process Latent Variable Models were used for the dimensionality reduction of the manifold of shapes and a two-step iteration optimizes over shape and pose, respectively [16] .”
Pattern Recognition (2015, unknown): “Beyond that, uncertainty and reliability of parameter estimates in bundle-adjustment only improve up to a certain redundancy [2,30], i.”
A Field Model for Repairing 3D Shapes (2016, methodology): “Alternatively, the object models can be constructed based on 2D image segmentation, e.g. [27], or 2D object detection.”