Estimating 3D shape from degenerate sequences with missing data

75 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.

Lifting Object Detection Datasets into 3D (2015, methodology): “Methods such as shape from shading (SfS) [43] hold great promise but have so far been applied only in very restricted settings as they make strong assumptions about global illumination conditions and the reﬂective properties of the object.”
WarpNet: Weakly Supervised Matching for Single-View Reconstruction (2016, methodology): “We finally send the observation matrix to the rigid factorization method of [21], which robustly handles missing data, to obtain 3D shape.”
Unifying Nuclear Norm and Bilinear Factorization Approaches for Low-Rank Matrix Decomposition (2013, background): “While there are certainly degenerate scenarios which can only be solved with such constraints [26], Alg.”
Reconstructing PASCAL VOC (2014, methodology): “A similar projection step is used in [19].”
Factorization for non-rigid and articulated structure using metric projections (2009, methodology): “An Active AppearanceModel (AAM) was used to track 68 features on the face.”
Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes (2014, methodology): “For these sequences, given the part and object segmentation results, we reconstruct each part independently with an orthographic factorization approach [23].”