Filters








73 Hits in 2.3 sec

Practical SVBRDF capture in the frequency domain

Miika Aittala, Tim Weyrich, Jaakko Lehtinen
2013 ACM Transactions on Graphics  
Middle: a photograph of a material sample, taken under a novel viewpoint and illumination not used in the capture. Right: our rendering with matching lighting and viewing conditions.  ...  Abstract Spatially-varying reflectance and small geometric variations play a vital role in the appearance of real-world surfaces.  ...  Acknowledgments Miika Aittala was supported by the HeCSE Graduate School and the MIDE program (project UI-ART) of Aalto University; Tim Weyrich was supported by the FP7 EU collaborative project BEAMING  ... 
doi:10.1145/2461912.2461978 fatcat:jiaxrdremzdy7pm7pizxe3lzo4

Manifold bootstrapping for SVBRDF capture

Yue Dong, Jiaping Wang, Xin Tong, John Snyder, Yanxiang Lan, Moshe Ben-Ezra, Baining Guo
2010 ACM Transactions on Graphics  
It provides a high-resolution result in both the spatial and angular domains by decomposing reflectance measurement into two lower-dimensional phases.  ...  We show that the resulting Ndimensional keys capture much of the distance information in the original BRDF space, so that they effectively discriminate among representatives, though they lack sufficient  ...  The parameter x represents the spatial domain component while i × o represents the angular domain component.  ... 
doi:10.1145/1778765.1778835 fatcat:vqmiumhxbrhtji6lxmecdxxbwy

Reflectance modeling by neural texture synthesis

Miika Aittala, Timo Aila, Jaakko Lehtinen
2016 ACM Transactions on Graphics  
This work was supported by the Academy of Finland (grant 277833). We acknowledge the computational resources provided by the Aalto Science-IT project.  ...  In practice, the prior is efficiently implemented in frequency domain.  ...  In practice, this means we internally represent the SVBRDF components as the conjugate symmetric parts of their Fourier transforms.  ... 
doi:10.1145/2897824.2925917 fatcat:ir6jtl4ypvahnkodmdkwd5qlla

Manifold bootstrapping for SVBRDF capture

Yue Dong, Jiaping Wang, Xin Tong, John Snyder, Yanxiang Lan, Moshe Ben-Ezra, Baining Guo
2010 ACM SIGGRAPH 2010 papers on - SIGGRAPH '10  
It provides a high-resolution result in both the spatial and angular domains by decomposing reflectance measurement into two lower-dimensional phases.  ...  We show that the resulting Ndimensional keys capture much of the distance information in the original BRDF space, so that they effectively discriminate among representatives, though they lack sufficient  ...  The parameter x represents the spatial domain component while i × o represents the angular domain component.  ... 
doi:10.1145/1833349.1778835 fatcat:auqlv7qvsrffloatovtdx43rce

Manifold bootstrapping for SVBRDF capture

Yue Dong, Jiaping Wang, Xin Tong, John Snyder, Yanxiang Lan, Moshe Ben-Ezra, Baining Guo
2010 ACM Transactions on Graphics  
It provides a high-resolution result in both the spatial and angular domains by decomposing reflectance measurement into two lower-dimensional phases.  ...  We show that the resulting Ndimensional keys capture much of the distance information in the original BRDF space, so that they effectively discriminate among representatives, though they lack sufficient  ...  The parameter x represents the spatial domain component while i × o represents the angular domain component.  ... 
doi:10.1145/1833351.1778835 fatcat:wkqwpl5rtveo5kjcjo3zbatqmq

SurfaceNet: Adversarial SVBRDF Estimation from a Single Image [article]

Giuseppe Vecchio, Simone Palazzo, Concetto Spampinato
2021 arXiv   pre-print
The employment of the GAN paradigm has a twofold objective: 1) allowing the model to recover finer details than standard translation models; 2) reducing the domain shift between synthetic and real data  ...  In this paper we present SurfaceNet, an approach for estimating spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image.  ...  Experimental results In this section, we first introduce the datasets employed in our work: the synthetic dataset with SVBRDF annotation, and the real dataset that we employ for unsupervised domain adaptation  ... 
arXiv:2107.11298v1 fatcat:c42nftoxpnbfrlpqgxxdlaeoiy

Reflectance scanning

Guojun Chen, Yue Dong, Pieter Peers, Jiawan Zhang, Xin Tong
2014 ACM Transactions on Graphics  
Acknowledgements We wish to thank the reviewers for their constuctive feedback. Pieter Peers was partially funded by NSF grants: IIS-1217765, IIS-1350323, and a gift from Google.  ...  point sampling in the frequency domain).  ...  We then compare the capture validation photograph with a visualization of the reconstructed SVBRDF under similar conditions.  ... 
doi:10.1145/2601097.2601180 fatcat:p2broeaqaverjjvvcy67hyta6e

Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image [article]

Zhengqin Li, Kalyan Sunkavalli, Manmohan Chandraker
2018 arXiv   pre-print
Our method images the surface under arbitrary environment lighting with the flash turned on, thereby avoiding shadows while simultaneously capturing high-frequency specular highlights.  ...  Our network is trained using a large-scale SVBRDF dataset and designed to incorporate physical insights for material estimation, including an in-network rendering layer to model appearance and a material  ...  In this work, we present a practical material capture method that can recover an SVBRDF from a single image of a near-planar surface, acquired using the camera of an off-the-shelf consumer mobile phone  ... 
arXiv:1804.05790v1 fatcat:yhpmf3t6ezgr5kmpzvq7mxjihm

Gamut Mapping Spatially Varying Reflectance with an Improved BRDF Similarity Metric

Thiago Pereira, Szymon Rusinkiewicz
2012 Computer graphics forum (Print)  
In this work, we present an svBRDF gamut mapping algorithm that minimizes distortions in the angular and spatial domains.  ...  As for the spatial domain, we show how to adapt traditional color gamut mapping methods to svBRDFs.  ...  We also thank Wojciech Matusik, Boris Ajdin, Jason Lawrence, and Paul Debevec for the BRDF, svBRDF, and environment-map datasets used in this paper.  ... 
doi:10.1111/j.1467-8659.2012.03152.x fatcat:zfnz52wzcfb5xb2weg6x6itotq

Generative Modelling of BRDF Textures from Flash Images [article]

Philipp Henzler, Valentin Deschaintre, Niloy J. Mitra, Tobias Ritschel
2021 arXiv   pre-print
subsequently allows rendering in complex scenes and illuminations, matching the appearance of the input photograph.  ...  Then, in the second step, conditioned on the material code, our method produces an infinite and diverse spatial field of BRDF model parameters (diffuse albedo, normals, roughness, specular albedo) that  ...  We thank the authors of Aittala et al. [2016] , Gao et al. [2019] , Guo et al. [2020b] , for providing their implementations and helping with the comparisons.  ... 
arXiv:2102.11861v2 fatcat:6me7cyt4jbhivbvpou3irpfuwi

Image-based separation of diffuse and specular reflections using environmental structured illumination

Bruce Lamond, Pieter Peers, Abhijeet Ghosh, Paul Debevec
2009 2009 IEEE International Conference on Computational Photography (ICCP)  
In both cases the low-pass filtering nature of diffuse reflections is utilized to separate the reflection components. We illustrate our method on a wide range of example scenes and applications.  ...  SVBRDF Estimation: We can use our separation method to capture and fit SVBRDFs. For simplicity we assume that the SVBRDF is isotropic, and that the diffuse reflection is Lambertian.  ...  The core idea is that diffuse reflections act as a low-pass filter in the incident angular domain, and can be separated using a band-pass filter.  ... 
doi:10.1109/iccphot.2009.5559012 fatcat:csfjgcb525eslilawpsncdvl44

Image-based appearance acquisition of effect coatings

Jiří Filip, Radomír Vávra
2019 Computational Visual Media  
In this paper we analyze several approaches to capturing spatially-varying appearances of effect coatings.  ...  images which must be captured.  ...  time they devoted to participation in visual experiments.  ... 
doi:10.1007/s41095-019-0134-3 fatcat:q5epkvomlvfxroovuzwt6gsinm

Principles of appearance acquisition and representation

Tim Weyrich, Jason Lawrence, Hendrik Lensch, Szymon Rusinkiewicz, Todd Zickler
2008 ACM SIGGRAPH 2008 classes on - SIGGRAPH '08  
To exploit spatial smoothness, we view each pixel as sample lying in the (5D isotropic) SVBRDF domain, and we note that each image provides a near-continuous sampling of a 2D slice in this domain.  ...  One real practical problem concerns scattered data interpolation. Keep in mind that these datasets often consist of measurements scattered across a high-dimensional domain.  ...  The respective Torrance-Sparrow parameters ρ s and m vary significantly in dependence of the facial region.  ... 
doi:10.1145/1401132.1401234 dblp:conf/siggraph/WeyrichLLRZ08 fatcat:3mgaott37ngs5kdmvqmhhr7uzu

Principles of Appearance Acquisition and Representation

Tim Weyrich, Jason Lawrence, Hendrik P. A. Lensch, Szymon Rusinkiewicz, Todd Zickler
2007 Foundations and Trends in Computer Graphics and Vision  
To exploit spatial smoothness, we view each pixel as sample lying in the (5D isotropic) SVBRDF domain, and we note that each image provides a near-continuous sampling of a 2D slice in this domain.  ...  One real practical problem concerns scattered data interpolation. Keep in mind that these datasets often consist of measurements scattered across a high-dimensional domain.  ...  The respective Torrance-Sparrow parameters ρ s and m vary significantly in dependence of the facial region.  ... 
doi:10.1561/0600000022 fatcat:7dro6xcvz5hotdxmr7yvvkvr3y

Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image

Zhengqin Li, Mohammad Shafiei, Ravi Ramamoorthi, Kalyan Sunkavalli, Manmohan Chandraker
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
incorporates physical insightsincluding a spatially-varying spherical Gaussian lighting representation, a differentiable rendering layer to model scene appearance, a cascade structure to iteratively refine the  ...  Our per-pixel SVSG lighting representation captures high frequency effects.  ...  An automatic, rendering-based optimization is proposed in [28] to estimate all these scene factors, but using strong heuristics that are often violated in practice.  ... 
doi:10.1109/cvpr42600.2020.00255 dblp:conf/cvpr/LiSRSC20 fatcat:rp7jmu65dzgjfhdfezb5edr2r4
« Previous Showing results 1 — 15 out of 73 results