Filters








71,696 Hits in 4.4 sec

Optimized Image Sampling for View and Light Interpolation [article]

Prabath Gunawardane, Oliver Wang, Steven Scher, Ian Rickards, James Davis, Tom Malzbender
2009 VAST: International Symposium on Virtual Reality  
We carry out an analysis on this combined lighting and view space to find the optimal sampling given a restricted image budget.  ...  However, acquiring a dense sampling of both the lighting and view space is time consuming.  ...  Acknowledgments Support for this work was provided by Cultural Heritage Imaging, UC CITRIS, LANL ISSDM, and NSF #CCF-  ... 
doi:10.2312/vast/vast09/093-100 fatcat:rd547lq4s5enphmtxmfdaz6m5y

A Geometric Analysis of Light Field Rendering

Zhouchen Lin, Heung-Yeung Shum
2004 International Journal of Computer Vision  
Our key observation is that anti-aliased light field rendering is equivalent to eliminating the "double image" artifacts caused by view interpolation.  ...  In this paper, we adopt a geometric approach to investigate the minimum sampling problem for light field rendering, with and without geometry information of the scene.  ...  The optimal motion compensation vector is (59 + 27)/(2 × (17 − 1)) = 2.6875 pixels between successive sample images. The real value of z min is insignificant.  ... 
doi:10.1023/b:visi.0000015916.91741.27 fatcat:ibpsyvgo6verfhjjfsqhb2a2ga

Shape, Light Material Decomposition from Images using Monte Carlo Rendering and Denoising [article]

Jon Hasselgren, Nikolai Hofmann, Jacob Munkberg
2022 arXiv   pre-print
This substantially improves convergence and enables gradient-based optimization at low sample counts.  ...  Recent advances in differentiable rendering have enabled high-quality reconstruction of 3D scenes from multi-view images.  ...  Light probe intensities, for example, are optimized based on an importance sampled image, which are then used to construct the sampling distribution for the subsequent pass.  ... 
arXiv:2206.03380v1 fatcat:jbpco4nfifgxjfysakedwxst4y

A Study of Efficient Light Field Subsampling and Reconstruction Strategies [article]

Yang Chen, Martin Alain, Aljosa Smolic
2020 arXiv   pre-print
In this paper, we study subsampling and reconstruction strategies for light fields.  ...  We evaluate these strategies on both real-world and synthetic datasets, and optimal selection strategies are devised from our results.  ...  In Section 2, we review existing methods for light field angular superresolution and more general techniques for view synthesis and video frame interpolation.  ... 
arXiv:2008.04694v1 fatcat:broru4bffvhojc7bzbswdob7le

SURFACE CAMERA (SCAM) LIGHT FIELD RENDERING

JINGYI YU, LEONARD MCMILLAN, STEVEN GORTLER
2004 International Journal of Image and Graphics  
We present an efficient rendering algorithm that combines ray samples from scams with those from the light field.  ...  The resulting image reconstructions are noticeably improved over that of a pure light field.  ...  Light field rendering is a special form of image-based rendering. It synthesizes new views by interpolating a set of sampled images without associated depth in-formation.  ... 
doi:10.1142/s0219467804001567 fatcat:j6zrqg6yfzdmhk54esvbd7fbjq

Self-supervised Light Field View Synthesis Using Cycle Consistency [article]

Yang Chen, Martin Alain, Aljosa Smolic
2020 arXiv   pre-print
However, collecting such large datasets for light fields is challenging compared to natural images or videos.  ...  Besides, our generic light field view synthesis framework can be adopted to any pre-trained model for advanced video interpolation.  ...  For all experiments, we set the parameters as λ c = 1, λ r = 1, and λ p = 0.06. The Adam optimizer is applied for optimization with a batch size of 8.  ... 
arXiv:2008.05084v1 fatcat:4vyotfvkfbbp5oao5m533sv2h4

Self-supervised Light Field View Synthesis Using Cycle Consistency

Yang Chen, Martin Alain, Aljosa Smolic
2020 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)  
However, collecting such large datasets for light fields is challenging compared to natural images or videos.  ...  Besides, our generic light field view synthesis framework can be adopted to any pre-trained model for advanced video interpolation.  ...  For all experiments, we set the parameters as λ c = 1, λ r = 1, and λ p = 0.06. The Adam optimizer is applied for optimization with a batch size of 8.  ... 
doi:10.1109/mmsp48831.2020.9287105 fatcat:e7oqiqqlprellew2wcie7icz44

Plenoxels: Radiance Fields without Neural Networks [article]

Alex Yu, Sara Fridovich-Keil, Matthew Tancik, Qinhong Chen, Benjamin Recht, Angjoo Kanazawa
2021 arXiv   pre-print
This representation can be optimized from calibrated images via gradient methods and regularization without any neural components.  ...  We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics.  ...  Additionally, we would like to thank Ren Ng for helpful suggestions and Hang Gao for reviewing a draft of the paper.  ... 
arXiv:2112.05131v1 fatcat:p6mhlt3r3va4ndtm4t7j3hjlb4

Using a Robotic Arm for Measuring BRDFs [chapter]

Rasmus Ahrenkiel Lyngby, Jannik Boll Matthiassen, Jeppe Revall Frisvad, Anders Bjorholm Dahl, Henrik Aanæs
2019 Lecture Notes in Computer Science  
Point-like light sources, fixed on a quarter circle arc, sequentially illuminate the sample from different directions. The resulting images are used to reconstruct the material BRDF.  ...  Our focus is on the alignment of the system to perform accurate camera positioning and orientation.  ...  Representation and Sample Interpolation A common format for storing BRDFs is the MERL binary format [9] .  ... 
doi:10.1007/978-3-030-20205-7_16 fatcat:elsh2txetfafnilwvlhgmz42bi

Light Field Implicit Representation for Flexible Resolution Reconstruction [article]

Paramanand Chandramouli, Hendrik Sommerhoff, Andreas Kolb
2021 arXiv   pre-print
This formulation enables us to reconstruct light field views at any desired spatial and angular resolution.  ...  We propose an implicit representation model for 4D light fields which is conditioned on a sparse set of input views.  ...  handle spatial sparsity with exception to [2] which requires expensive optimization for view interpolation, and can only generate views of fixed angular resolution.  ... 
arXiv:2112.00185v1 fatcat:jr5cwcnzprdnhmemxj7jbqeabm

Adaptive scanning optical microscope (ASOM): large field of view and high resolution imaging using a MEMS deformable mirror

Benjamin Potsaid, Linda Ivonne Rivera, John Ting-Yung Wen, Scot S. Olivier, Thomas G. Bifano, Joel A. Kubby
2007 MEMS Adaptive Optics  
For a wide range of applications in biology, medicine, and manufacturing, the small field of view associated with high resolution microscope systems poses a significant challenge in practice.  ...  With the rapid scanning capabilities allowed by the high speed steering mirror and by acquiring a complete image during each exposure, the ASOM offers advantages in dynamically reconfigurable and adaptable  ...  Because it is not practical to optimize for every possible field position, we optimize a grid sampling of points over the entire observable field of view and use interpolation of the deformable mirror  ... 
doi:10.1117/12.700538 fatcat:jr5ymnpr75bkrkzwcd64qhvude

Adaptive scanning optical microscope: large field of view and high-resolution imaging using a MEMS deformable mirror

Benjamin Potsaid
2008 Journal of Micro/Nanolithography  
For a wide range of applications in biology, medicine, and manufacturing, the small field of view associated with high resolution microscope systems poses a significant challenge in practice.  ...  With the rapid scanning capabilities allowed by the high speed steering mirror and by acquiring a complete image during each exposure, the ASOM offers advantages in dynamically reconfigurable and adaptable  ...  Because it is not practical to optimize for every possible field position, we optimize a grid sampling of points over the entire observable field of view and use interpolation of the deformable mirror  ... 
doi:10.1117/1.2909451 fatcat:n5sqzawx3bhclcd2nawg3zwoyy

Statistical Acquisition of Texture Appearance [article]

Addy Ngan, Frédo Durand
2006 Symposium on Rendering  
Bidirectional properties are acquired from a sparse set of viewing directions through image statistics and therefore precise registrations for these views are unnecessary.  ...  Our technique renders elaborate view- and light-dependent effects and faithfully reproduces materials such as fabrics and knitwears.  ...  Tom Buehler produced the accompanying video, and Robert Wang created the cloth mesh. We acknowledge BTF Database Bonn and Koudelka et al. for sharing their BTF measurements.  ... 
doi:10.2312/egwr/egsr06/031-040 fatcat:k534lgojvjfdxni7lxlm5xdn7m

On optimal resampling of view and illumination dependent textures

Jiří Filip, Michael J. Chantler, Michal Haindl
2008 Proceedings of the 5th symposium on Applied perception in graphics and visualization - APGV '08  
Perceptually-based methods can determine optimal uniform resampling of these data that allows considerable reduction of a number of view and illumination dependent samples.  ...  The resampling was done separately for elevation and azimuthal angles as well as in illumination and view space.  ...  Acknowledgments: This research was supported by the EC Marie-Curie IEF No.41358, the EPSRC SMI grants GR/S12395/01 and EP/F02553X/1, and the GAČR grant 102/08/0593.  ... 
doi:10.1145/1394281.1394305 dblp:conf/apgv/FilipCH08 fatcat:imnkyinz25ewpirl5cgbwcyrfi

Grid Based Final Gather for Radiosity on Complex Clustered Scenes

Annette Scheel, Marc Stamminger, Hans-Peter Seidel
2002 Computer graphics forum (Print)  
We further reduce the number of required samples using view-dependent optimizations.  ...  To reconstruct a high quality image, usually a second very time consuming final gather pass is applied which exactly recomputes the last light transport before reaching the eye.  ...  We furthermore enhance the method by view dependent optimizations, taking into account visual masking of the human visual system, and image sample resolution.  ... 
doi:10.1111/1467-8659.t01-1-00705 fatcat:ytc52wwmsnh43lhukzjxni6dbq
« Previous Showing results 1 — 15 out of 71,696 results