Filters








71 Hits in 2.6 sec

Compressive Neural Representations of Volumetric Scalar Fields [article]

Yuzhe Lu, Kairong Jiang, Joshua A. Levine, Matthew Berger
2021 arXiv   pre-print
We present an approach for compressing volumetric scalar fields using implicit neural representations.  ...  Our approach represents a scalar field as a learned function, wherein a neural network maps a point in the domain to an output scalar value.  ...  Weiss et al. developed new techniques for isosurface rendering that similarly used deep learning for super-resolution [WCTW19].  ... 
arXiv:2104.04523v1 fatcat:tcvnvgoppjbkxpjpukatc6aapu

Learning Adaptive Sampling and Reconstruction for Volume Visualization [article]

Sebastian Weiss, Mustafa Işık, Justus Thies, Rüdiger Westermann
2020 arXiv   pre-print
We introduce a novel neural rendering pipeline, which is trained end-to-end to generate a sparse adaptive sampling structure from a given low-resolution input image, and reconstructs a high-resolution  ...  We shed light on the adaptive sampling patterns generated by the network pipeline and analyze its use for volume visualization including isosurface and direct volume rendering.  ...  [18] designed a deep learning framework that produces coherent spatial super-resolution of 3D vector field data. Weiss et al.  ... 
arXiv:2007.10093v1 fatcat:o7ddk6ypurce5hhf6c2ekfqcle

Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis [article]

Angela Dai, Charles Ruizhongtai Qi, Matthias Nießner
2017 arXiv   pre-print
We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis.  ...  We then correlate these intermediary results with 3D geometry from a shape database at test time.  ...  We compare favorably, even only the 3D-EPN, but final shape synthesis increases the resolution and adds additional geometric detail.  ... 
arXiv:1612.00101v2 fatcat:j2y5z5hv6vbypf767eu2kbrzj4

Occupancy Networks: Learning 3D Reconstruction in Function Space

Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, Andreas Geiger
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity.  ...  We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks.  ...  Voxel Super-Resolution As a final conditional task, we apply occupancy networks to 3D super-resolution [62] .  ... 
doi:10.1109/cvpr.2019.00459 dblp:conf/cvpr/MeschederONNG19 fatcat:ap2axpywwfgo5l7v5oy6f6cg3i

Occupancy Networks: Learning 3D Reconstruction in Function Space [article]

Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, Andreas Geiger
2019 arXiv   pre-print
With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity.  ...  We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks.  ...  Voxel Super-Resolution As a final conditional task, we apply occupancy networks to 3D super-resolution [62] .  ... 
arXiv:1812.03828v2 fatcat:jyk7zrqhnveexbogshq7nrc4ee

Deep Volumetric Ambient Occlusion [article]

Dominik Engel, Timo Ropinski
2020 arXiv   pre-print
We present a novel deep learning based technique for volumetric ambient occlusion in the context of direct volume rendering.  ...  Based on the obtained results we also give recommendations applicable in similar volume learning scenarios.  ...  The renderings have been produced using Inviwo [19] (www.inviwo.org).  ... 
arXiv:2008.08345v1 fatcat:o3577alddvgebagyoheo3rdyay

Deep Hierarchical Super-Resolution for Scientific Data Reduction and Visualization [article]

Skylar W. Wurster, Han-Wei Shen, Hanqi Guo, Thomas Peterka, Mukund Raj, Jiayi Xu
2021 arXiv   pre-print
, scaling with the number of trained networks.  ...  We present an approach for hierarchical super resolution (SR) using neural networks on an octree data representation.  ...  super resolution algorithm for an octree-based data representation that upscales multiresolution data to a uniform resolution with minimal seam artifacts.  ... 
arXiv:2107.00462v1 fatcat:37qe5d6v4bgrzb3cy5fnzf2qjm

DeepSTORM3D: dense three dimensional localization microscopy and point spread function design by deep learning [article]

Elias Nehme, Daniel Freedman, Racheli Gordon, Boris Ferdman, Lucien E. Weiss, Onit Alalouf, Reut Orange, Tomer Michaeli, Yoav Shechtman
2019 arXiv   pre-print
This is the key ingredient in single/multiple-particle-tracking and several super-resolution microscopy approaches.  ...  The PSF is engineered using additional optical elements to vary distinctively with the depth of the point-source.  ...  We also thank Jonas Ries for his help with the application of SMAP-2018 to Tetrapod PSFs.  ... 
arXiv:1906.09957v2 fatcat:hbd6ll4cfvbrdibur2prpqspk4

InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations

Wenbin He, Junpeng Wang, Hanqi Guo, Ko-Chih Wang, Han-Wei Shen, Mukund Raj, Youssef S. G. Nashed, Tom Peterka
2019 IEEE Transactions on Visualization and Computer Graphics  
We propose InSituNet, a deep learning based surrogate model to support parameter space exploration for ensemble simulations that are visualized in situ.  ...  Our approach allows flexible exploration of parameter space for large-scale ensemble simulations by taking advantage of the recent advances in deep learning.  ...  Our work is related to deep learning based image synthesis, which has been used in various applications, including super-resolution [18, 32, 36] , denoising [68, 70] , inpainting [46, 68] , texture  ... 
doi:10.1109/tvcg.2019.2934312 pmid:31425097 fatcat:wxyjj5yjyvdz7lkdnqzqp7l3wy

Learning Shape Priors for Single-View 3D Completion And Reconstruction [chapter]

Jiajun Wu, Chengkai Zhang, Xiuming Zhang, Zhoutong Zhang, William T. Freeman, Joshua B. Tenenbaum
2018 Lecture Notes in Computer Science  
In this paper, we propose ShapeHD, pushing the limit of single-view shape completion and reconstruction by integrating deep generative models with adversarially learned shape priors.  ...  Recent research in the field has tackled this problem by exploiting the expressiveness of deep convolutional networks.  ...  To tackle this, we propose ShapeHD, which completes or reconstructs a 3D shape by combining deep volumetric convolutional networks with adversarially learned shape priors.  ... 
doi:10.1007/978-3-030-01252-6_40 fatcat:hb2hfm5cgvho3h63owzvhfwczi

Learning Shape Priors for Single-View 3D Completion and Reconstruction [article]

Jiajun Wu, Chengkai Zhang, Xiuming Zhang, Zhoutong Zhang, William T. Freeman, Joshua B. Tenenbaum
2018 arXiv   pre-print
In this paper, we propose ShapeHD, pushing the limit of single-view shape completion and reconstruction by integrating deep generative models with adversarially learned shape priors.  ...  Recent research in the field has tackled this problem by exploiting the expressiveness of deep convolutional networks.  ...  To tackle this, we propose ShapeHD, which completes or reconstructs a 3D shape by combining deep volumetric convolutional networks with adversarially learned shape priors.  ... 
arXiv:1809.05068v1 fatcat:jd24yzcwkvcaflxh6wqxqhujce

3D SCENE RECONSTRUCTION SYSTEM BASED ON A MOBILE DEVICE

2021 IADIS International Journal on Computer Science and Information System  
A smartphone can be used to take a photo of the object under analysis and a remote server performs the reconstruction process by exploiting a pipeline of three Deep Learning methods.  ...  Accuracy and robustness of the system have been assessed by several experiments and the main outcomes show how the proposed solution has a comparable accuracy (chamfer distance) with the state-of-the-art  ...  RELATED WORK Deep Learning-Based 3D Object Reconstruction Methods Several methods for 3D object reconstruction based on Deep Learning that produce three-dimensional assets from a single or multiple images  ... 
doi:10.33965/ijcsis_2021160202 fatcat:ty5bhde44fe5hf6tf4mzupqehi

Scientific Visualization (Dagstuhl Seminar 11231)

Min Chen, Hans Hagen, Charles D. Hansen, Arie Kaufman, Marc Herbstritt
2011 Dagstuhl Reports  
Reflecting the heterogeneous structure of Scientific Visualization and the currently unsolved problems in the field, this seminar dealt with key research problems and their solutions in the following subfields  ...  In particular, we show how to approximate topological structures from hixel data, extract structures from multi-modal distributions, and render uncertain isosurfaces.  ...  rendering.  ... 
doi:10.4230/dagrep.1.6.1 dblp:journals/dagstuhl-reports/ChenHHK11 fatcat:jvdbpd4q3fddjazkxyhttih36a

Correlated Multimodal Imaging in Life Sciences: Expanding the Biomedical Horizon

Andreas Walter, Perrine Paul-Gilloteaux, Birgit Plochberger, Ludek Sefc, Paul Verkade, Julia G. Mannheim, Paul Slezak, Angelika Unterhuber, Martina Marchetti-Deschmann, Manfred Ogris, Katja Bühler, Dror Fixler (+5 others)
2020 Frontiers in Physics  
The review is in line with major European initiatives, such as COMULIS (CA17121), a COST Action to promote and foster Correlated Multimodal Imaging in Life Sciences.  ...  to relocate the same region of interest (ROI) after transfer between imaging platforms including fiducial markers, and (3) automated software solutions to correlate complex, multiscale, multimodal and volumetric  ...  super-resolution FM.  ... 
doi:10.3389/fphy.2020.00047 fatcat:ncyaxrt6ijgubp6sdgujyoq6yi

Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids [article]

Bruno Roy, Pierre Poulin, Eric Paquette
2021 arXiv   pre-print
We present a novel up-resing technique for generating high-resolution liquids based on scene flow estimation using deep neural networks.  ...  Our approach infers and synthesizes small- and large-scale details solely from a low-resolution particle-based liquid simulation.  ...  CONCLUSION AND FUTURE WORK We have presented an approach leveraging deep learning to increase the apparent resolution of a coarse particle-based liquid.  ... 
arXiv:2106.05143v1 fatcat:yzb76xpbrrbstnyi6c7nwqnvby
« Previous Showing results 1 — 15 out of 71 results