Results 1 to 10 of about 882 (37)

Computational advances in gravitational microlensing: a comparison of CPU, GPU, and parallel, large data codes [PDF]

, 2010
To assess how future progress in gravitational microlensing computation at high optical depth will rely on both hardware and software solutions, we compare a direct inverse ray-shooting code implemented on a graphics processing unit (GPU) with both a ...
Abajas, Alcock, Anguita, Aubourg, B.R. Barsdell, Barnes, Bate, Belleman, Bond, C.J. Fluke, Calchi Novati, Chang, Chartas, Dai, Eigenbrod, Floyd, Ford, Fournier, G.F. Lewis, Garsden, Gould, Gould, H. Garsden, Harris, Irwin, Kayser, Keeton, Kochanek, Lewis, Lewis, Mediavilla, Mediavilla, Morgan, N.F. Bate, Owens, Poindexter, Pooley, Pooley, Rauch, Schive, Schneider, Schneider, Schneider, Sumi, Thompson, Udalski, Vanderriest, Wambsganss, Wambsganss, Wambsganss, Witt, Witt, Wyithe, Wyithe, Wyrzykowski   +54 more
core   +4 more sources

Hyperparameter-free losses for model-based monocular reconstruction [PDF]

, 2019
This work proposes novel hyperparameter-free losses for single view 3D reconstruction with morphable models (3DMM). We dispense with the hyperparameters used in other works by exploiting geometry, so that the shape of the object and the camera pose are ...
Batard, Thomas, Giró Nieto, Xavier, Ramon Maldonado, Eduard, Ruiz, Guillermo   +3 more
core   +2 more sources

3D Car Shape Reconstruction from a Single Sketch Image [PDF]

, 2019
Efficient car shape design is a challenging problem in both the automotive industry and the computer animation/games industry. In this paper, we present a system to reconstruct the 3D car shape from a single 2D sketch image.
Ho, Edmond, Morishima, Shigeo, Nozawa, Naoiki, Shum, Hubert   +3 more
core   +1 more source

Gleam: the GLAST Large Area Telescope Simulation Framework

, 2003
This paper presents the simulation of the GLAST high energy gamma-ray telescope. The simulation package, written in C++, is based on the Geant4 toolkit, and it is integrated into a general framework used to process events.
Claudia Cecchi G, Dario Favretto A, Denis Bastieri N, Edoardo Milotti A, Francesco Longo L, Francesco Loparco D, Gargano D, Gloria Sp, Joanne Bogart E, Johann Cohen-tanugi C, Latronico C, Leon Rochester E, Luca Baldini C, Marco Frailis A, Mario Nicola, Mazziotta D, Michael Kuss C, Monica Brigida D, Monica Pepe G, Nicola Giglietto D, Nicola Omodei C, Pasquale Lubrano G, Praveen Boinee A, Re C, Riccardo Giannitrapani A, Riccardo R, Richard Dubois E, Ro De Angelis A, Sean Robinson F, Toby Burnett F, Tracy Usher E, Tune Kamae E   +31 more
core   +5 more sources

Learning quadrangulated patches for 3D shape parameterization and completion

, 2017
We propose a novel 3D shape parameterization by surface patches, that are oriented by 3D mesh quadrangulation of the shape. By encoding 3D surface detail on local patches, we learn a patch dictionary that identifies principal surface features of the ...
Sarkar, Kripasindhu, Stricker, Didier, Varanasi, Kiran   +2 more
core   +1 more source

Learning to Group and Label Fine-Grained Shape Components

, 2018
A majority of stock 3D models in modern shape repositories are assembled with many fine-grained components. The main cause of such data form is the component-wise modeling process widely practiced by human modelers.
Chen, Xiaowu, Fang, Haiyue, Wang, Xiaogang, Xu, Kai, Zhao, Qinping, Zhou, Bin   +5 more
core   +1 more source

PhotoShape: Photorealistic Materials for Large-Scale Shape Collections

, 2018
Existing online 3D shape repositories contain thousands of 3D models but lack photorealistic appearance. We present an approach to automatically assign high-quality, realistic appearance models to large scale 3D shape collections.
Farhadi, Ali, Park, Keunhong, Rematas, Konstantinos, Seitz, Steven M.   +3 more
core   +1 more source

Hierarchical Surface Prediction for 3D Object Reconstruction

, 2017
Recently, Convolutional Neural Networks have shown promising results for 3D geometry prediction. They can make predictions from very little input data such as a single color image.
Häne, Christian, Malik, Jitendra, Tulsiani, Shubham   +2 more
core   +1 more source

MeshAdv: Adversarial Meshes for Visual Recognition

, 2019
Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming to mislead the ...
Deng, Jia, Li, Bo, Liu, Mingyan, Xiao, Chaowei, Yang, Dawei   +4 more
core   +1 more source

Unsupervised Deep Single-Image Intrinsic Decomposition using Illumination-Varying Image Sequences

, 2018
Machine learning based Single Image Intrinsic Decomposition (SIID) methods decompose a captured scene into its albedo and shading images by using the knowledge of a large set of known and realistic ground truth decompositions.
Bonneel N., Bonneel N., Garces E., Lalonde J.‐F., Meka A.   +4 more
core   +2 more sources