23 citations · 52 across the 7 of their papers we have counts for
9 papers
Möbius Convolutions for Spherical CNNs
Thomas W. Mitchel, Noam Aigerman, Vladimir G. Kim +1
Möbius transformations play an important role in both geometry and spherical image processing - they are the group of conformal automorphisms of 2D surfaces and the spherical equiv…
Field Convolutions for Surface CNNs
Thomas W. Mitchel, Vladimir G. Kim, Michael Kazhdan
We present a novel surface convolution operator acting on vector fields that is based on a simple observation: instead of combining neighboring features with respect to a single co…
Continuous body 3-D reconstruction of limbless animals
Qiyuan Fu, Thomas W. Mitchel, Jin Seob Kim +2
Limbless animals such as snakes, limbless lizards, worms, eels, and lampreys move their slender, long bodies in three dimensions to traverse diverse environments. Accurately quanti…
Efficient Spatially Adaptive Convolution and Correlation
Thomas W. Mitchel, Benedict Brown, David Koller +3
Fast methods for convolution and correlation underlie a variety of applications in computer vision and graphics, including efficient filtering, analysis, and simulation. However, s…
Lateral oscillation and body compliance help snakes and snake robots stably traverse large, smooth obstacles
Qiyuan Fu, Sean W. Gart, Thomas W. Mitchel +3
Snakes can move through almost any terrain. Similarly, snake robots hold the promise as a versatile platform to traverse complex environments like earthquake rubble. Unlike snake l…
Snakes partition their body to traverse large steps stably
Sean W. Gart, Thomas W. Mitchel, Chen Li
Many snakes live in deserts, forests, and river valleys and traverse challenging 3-D terrain like rocks, felled trees, and rubble, with obstacles as large as themselves and variabl…
Quotienting Impertinent Camera Kinematics for 3D Video Stabilization
Thomas W. Mitchel, Christian Wuelker, Jin Seob Kim +2
With the recent advent of methods that allow for real-time computation, dense 3D flows have become a viable basis for fast camera motion estimation. Most importantly, dense flows a…
Signal Alignment for Humanoid Skeletons via the Globally Optimal Reparameterization Algorithm
Thomas W. Mitchel, Sipu Ruan, Gregory S. Chirikjian
The general ability to analyze and classify the 3D kinematics of the human form is an essential step in the development of socially adept humanoid robots. A variety of different ty…
The Globally Optimal Reparameterization Algorithm: an Alternative to Fast Dynamic Time Warping for Action Recognition in Video Sequences
Thomas Mitchel, Sipu Ruan, Yixin Gao +1
Signal alignment has become a popular problem in robotics due in part to its fundamental role in action recognition. Currently, the most successful algorithms for signal alignment…