Search Results for author: Matthew Purri

Found 7 papers, 2 papers with code

Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks

1 code implementation3 Dec 2021 Peri Akiva, Matthew Purri, Matthew Leotta

By extension, effective representation of material and texture can describe other semantic classes strongly associated with said material and texture.

Change Detection Representation Learning +3

Shape From Sky: Polarimetric Normal Recovery Under the Sky

no code implementations CVPR 2021 Tomoki Ichikawa, Matthew Purri, Ryo Kawahara, Shohei Nobuhara, Kristin Dana, Ko Nishino

That is, we show that the unique polarization pattern encoded in the polarimetric appearance of an object captured under the sky can be decoded to reveal the surface normal at each pixel.

Street to Cloud: Improving Flood Maps With Crowdsourcing and Semantic Segmentation

no code implementations5 Nov 2020 Veda Sunkara, Matthew Purri, Bertrand Le Saux, Jennifer Adams

To address the mounting destruction caused by floods in climate-vulnerable regions, we propose Street to Cloud, a machine learning pipeline for incorporating crowdsourced ground truth data into the segmentation of satellite imagery of floods.

Semantic Segmentation

H2O-Net: Self-Supervised Flood Segmentation via Adversarial Domain Adaptation and Label Refinement

no code implementations11 Oct 2020 Peri Akiva, Matthew Purri, Kristin Dana, Beth Tellman, Tyler Anderson

We demonstrate that H2O-Net outperforms the state-of-the-art semantic segmentation methods on satellite imagery by 10% and 12% pixel accuracy and mIoU respectively for the task of flood segmentation.

Domain Adaptation Semantic Segmentation

Angular Luminance for Material Segmentation

no code implementations22 Sep 2020 Jia Xue, Matthew Purri, Kristin Dana

We demonstrate the increased performance of AngLNet over prior state-of-the-art in material segmentation from satellite imagery.

Material Recognition Object Recognition +1

Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images

1 code implementation ECCV 2020 Matthew Purri, Kristin Dana

The connection between visual input and tactile sensing is critical for object manipulation tasks such as grasping and pushing.

Neural Architecture Search

Material Segmentation of Multi-View Satellite Imagery

no code implementations17 Apr 2019 Matthew Purri, Jia Xue, Kristin Dana, Matthew Leotta, Dan Lipsa, Zhixin Li, Bo Xu, Jie Shan

The residuals are computed by differencing the sparse-sampled reflectance function with a dictionary of pre-defined dense-sampled reflectance functions.

Material Recognition Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.