activity
20182024
most citedRecurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth

41 citations · 55 across the 9 of their papers we have counts for

collaborators

9 papers

stat.ME2024

Model Fitting and Analysis of the Discrete Swept Skeletal Representation for Ellipsoidal Objects

Mohsen Taheri, Stephen M. Pizer, Jörn Schulz

Statistical shape analysis of quasi-ellipsoidal objects, such as groups of hippocampi, is crucial for advancing medical research by aiding in the diagnosis and understanding of var…

cs.CV2024

Interior Object Geometry via Fitted Frames

Stephen M. Pizer, Zhiyuan Liu, Junjie Zhao +6

We propose a means of computing fitted frames on the boundary and in the interior of objects and using them to provide the basis for producing geometric features from them that are…

stat.ME2024

The Mean Shape under the Relative Curvature Condition

Mohsen Taheri, Stephen M. Pizer, Jörn Schulz

Guaranteeing that Fréchet means of object populations do not locally self-intersect or are thereby affected is a serious challenge for object representations because the objects' s…

cs.CV2023

A Surface-normal Based Neural Framework for Colonoscopy Reconstruction

Shuxian Wang, Yubo Zhang, Sarah K. McGill +4

Reconstructing a 3D surface from colonoscopy video is challenging due to illumination and reflectivity variation in the video frame that can cause defective shape predictions. Aimi…

eess.IV2021★ 5 cited

ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction

Yubo Zhang, Jan-Michael Frahm, Samuel Ehrenstein +4

One of the key elements of reconstructing a 3D mesh from a monocular video is generating every frame's depth map. However, in the application of colonoscopy video reconstruction, p…

stat.ML2021

Non-Euclidean Analysis of Joint Variations in Multi-Object Shapes

Zhiyuan Liu, Jörn Schulz, Mohsen Taheri +4

This paper considers joint analysis of multiple functionally related structures in classification tasks. In particular, our method developed is driven by how functionally correlate…