Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Sarna, Aaron"'
Autor:
Geraedts, Scott, Brand, Erica, Dean, Thomas R., Eastham, Sebastian, Elkin, Carl, Engberg, Zebediah, Hager, Ulrike, Langmore, Ian, McCloskey, Kevin, Ng, Joe Yue-Hei, Platt, John C., Sankar, Tharun, Sarna, Aaron, Shapiro, Marc, Goyal, Nita
Persistent contrails make up a large fraction of aviation's contribution to global warming. We describe a scalable, automated detection and matching (ADM) system to determine from satellite data whether a flight has made a persistent contrail. The AD
Externí odkaz:
http://arxiv.org/abs/2308.02707
Autor:
Ng, Joe Yue-Hei, McCloskey, Kevin, Cui, Jian, Meijer, Vincent R., Brand, Erica, Sarna, Aaron, Goyal, Nita, Van Arsdale, Christopher, Geraedts, Scott
Contrails (condensation trails) are line-shaped ice clouds caused by aircraft and are likely the largest contributor of aviation-induced climate change. Contrail avoidance is potentially an inexpensive way to significantly reduce the climate impact o
Externí odkaz:
http://arxiv.org/abs/2304.02122
Autor:
Mishra, Shlok, Robinson, Joshua, Chang, Huiwen, Jacobs, David, Sarna, Aaron, Maschinot, Aaron, Krishnan, Dilip
We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise pred
Externí odkaz:
http://arxiv.org/abs/2210.16870
Disentangled visual representations have largely been studied with generative models such as Variational AutoEncoders (VAEs). While prior work has focused on generative methods for disentangled representation learning, these approaches do not scale t
Externí odkaz:
http://arxiv.org/abs/2108.06613
Autor:
Khosla, Prannay, Teterwak, Piotr, Wang, Chen, Sarna, Aaron, Tian, Yonglong, Isola, Phillip, Maschinot, Aaron, Liu, Ce, Krishnan, Dilip
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models. Modern batch contrastive approaches subsume or s
Externí odkaz:
http://arxiv.org/abs/2004.11362
The goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape categories, and inference from de
Externí odkaz:
http://arxiv.org/abs/1912.06126
Autor:
Teterwak, Piotr, Sarna, Aaron, Krishnan, Dilip, Maschinot, Aaron, Belanger, David, Liu, Ce, Freeman, William T.
Image extension models have broad applications in image editing, computational photography and computer graphics. While image inpainting has been extensively studied in the literature, it is challenging to directly apply the state-of-the-art inpainti
Externí odkaz:
http://arxiv.org/abs/1908.07007
Autor:
Genova, Kyle, Cole, Forrester, Vlasic, Daniel, Sarna, Aaron, Freeman, William T., Funkhouser, Thomas
Template 3D shapes are useful for many tasks in graphics and vision, including fitting observation data, analyzing shape collections, and transferring shape attributes. Because of the variety of geometry and topology of real-world shapes, previous me
Externí odkaz:
http://arxiv.org/abs/1904.06447
Autor:
Genova, Kyle, Cole, Forrester, Maschinot, Aaron, Sarna, Aaron, Vlasic, Daniel, Freeman, William T.
Publikováno v:
Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8377-8386
We present a method for training a regression network from image pixels to 3D morphable model coordinates using only unlabeled photographs. The training loss is based on features from a facial recognition network, computed on-the-fly by rendering the
Externí odkaz:
http://arxiv.org/abs/1806.06098
Autor:
Cole, Forrester, Belanger, David, Krishnan, Dilip, Sarna, Aaron, Mosseri, Inbar, Freeman, William T.
We present a method for synthesizing a frontal, neutral-expression image of a person's face given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition netwo
Externí odkaz:
http://arxiv.org/abs/1701.04851