Search Results for author:
Found 6 papers, 5 papers with code
Interpolated SelectionConv for Spherical Images and Surfaces
Our approach represents the surface as a graph of connected points that doesn't rely on a particular sampling strategy.
Ranked #22 on
Semantic Segmentation
on Stanford2D3D Panoramic
SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data
This network can then operate on any data that can be represented as a positional graph.
End-to-end Document Recognition and Understanding with Dessurt
Dessurt is a more flexible model than prior methods and is able to handle a variety of document domains and tasks.
Ranked #31 on
Visual Question Answering (VQA)
on DocVQA test
Text and Style Conditioned GAN for Generation of Offline Handwriting Lines
This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors.
Style Transfer for Light Field Photography
Thus, it is necessary to adapt existing monocular style transfer networks in a way that allows for the stylization of each view of the light field while maintaining visual consistencies between views.
Deep Visual Template-Free Form Parsing
Automatic, template-free extraction of information from form images is challenging due to the variety of form layouts.
