Filters








485 Hits in 3.9 sec

Two-shot Spatially-varying BRDF and Shape Estimation [article]

Mark Boss, Varun Jampani, Kihwan Kim, Hendrik P.A. Lensch, Jan Kautz
2020 arXiv   pre-print
Capturing the shape and spatially-varying appearance (SVBRDF) of an object from images is a challenging task that has applications in both computer vision and graphics.  ...  We follow a practical mobile image capture setting and use unaligned two-shot flash and no-flash images as input. Both our two-shot image capture and network inference can run on mobile hardware.  ...  Since the material properties can vary across the surface, one has to estimate the BRDF at each image pixel for a more realistic appearance (i.e., spatially-varying BRDF (SVBRDF)).  ... 
arXiv:2004.00403v1 fatcat:7fn3mfiarze3rkep6sfax6m7ru

SVBRDF-Invariant Shape and Reflectance Estimation from Light-Field Cameras

Ting-Chun Wang, Manmohan Chandraker, Alexei A. Efros, Ravi Ramamoorthi
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we derive a spatially-varying (SV)BRDF-invariant theory for recovering 3D shape and reflectance from lightfield cameras.  ...  Light-field cameras have recently emerged as a powerful tool for one-shot passive 3D shape capture.  ...  with spatially-varying BRDFs.  ... 
doi:10.1109/cvpr.2016.588 dblp:conf/cvpr/WangCER16 fatcat:cvcl2xj7d5ehlfjaie6ikrfqiq

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

Zhengqin Li, Kalyan Sunkavalli, Manmohan Chandraker
2018 Lecture Notes in Computer Science  
We propose a material acquisition approach to recover the spatially-varying BRDF and normal map of a near-planar surface from a single image captured by a handheld mobile phone camera.  ...  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  ...  Li and M. Chandraker are supported by NSF CAREER 1751365 and gratefully acknowledge funding from Adobe, BASF, Cognex and Snap. This work was partially done during Z. Li's summer internship at Adobe.  ... 
doi:10.1007/978-3-030-01219-9_5 fatcat:jtb634xczrc2hfokzxlxpjxldy

Minimal BRDF sampling for two-shot near-field reflectance acquisition

Zexiang Xu, Jannik Boll Nielsen, Jiyang Yu, Henrik Wann Jensen, Ravi Ramamoorthi
2016 ACM Transactions on Graphics  
Our framework generalizes to configurations like a fixed camera setup, where we also develop a simple extension to spatially-varying BRDFs by clustering the materials.  ...  We develop a method to acquire the BRDF of a homogeneous flat sample from only two images, taken by a near-field perspective camera, and lit by a directional light source.  ...  This work was supported by NSF grants 1451828, 1451830, and the UC San Diego Center for Visual Computing.  ... 
doi:10.1145/2980179.2982396 fatcat:6l732egqangt5olavh2piiouym

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

Zhengqin Li, Kalyan Sunkavalli, Manmohan Chandraker
2018 arXiv   pre-print
We propose a material acquisition approach to recover the spatially-varying BRDF and normal map of a near-planar surface from a single image captured by a handheld mobile phone camera.  ...  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  ...  Further Comparisons with Prior Works Comparison with two-shot BRDF method [8] The two-shot method of [8] can only handle images with stationary texture while our method can reconstruct arbitrarily  ... 
arXiv:1804.05790v1 fatcat:yhpmf3t6ezgr5kmpzvq7mxjihm

Single-Shot Specular Surface Reconstruction with Gonio-Plenoptic Imaging

Lingfei Meng, Liyang Lu, Noah Bedard, Kathrin Berkner
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
We present a gonio-plenoptic imaging system that realizes a single-shot shape measurement for specular surfaces. The system is comprised of a collimated illumination source and a plenoptic camera.  ...  simulations and experiments.  ...  [6] proposed a photometric stereo method for surfaces with spatially-varying BRDF.  ... 
doi:10.1109/iccv.2015.392 dblp:conf/iccv/MengLBB15 fatcat:fmtdnrpwsjgv3dlce6gvhoyrjm

Capturing Relightable Human Performances under General Uncontrolled Illumination

Guannan Li, Chenglei Wu, Carsten Stoll, Yebin Liu, Kiran Varanasi, Qionghai Dai, Christian Theobalt
2013 Computer graphics forum (Print)  
Finally, the high-quality all-frequency illumination is utilized to reconstruct the spatially-varying BRDF of the surface.  ...  The recovered time-varying surface geometry and spatially-varying non-Lambertian reflectance allow us to generate high-quality model-based free view-point videos of the actor under novel illumination conditions  ...  [GCHS05] reconstruct shape and spatially-varying BRDF via photometric stereo from images under controlled lighting. Carceroni et al.  ... 
doi:10.1111/cgf.12047 fatcat:hsxhjqbjtndrzo3d3twnsp3e3m

Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition [article]

Mark Boss, Varun Jampani, Raphael Braun, Ce Liu, Jonathan T. Barron, Hendrik P.A. Lensch
2021 arXiv   pre-print
We propose a novel reflectance decomposition network that can estimate shape, BRDF, and per-image illumination given a set of object images captured under varying illumination.  ...  Our decompositions can result in considerably better BRDF and light estimates enabling more accurate novel view-synthesis and relighting compared to prior art.  ...  Acknowledgments and Disclosure of Funding  ... 
arXiv:2110.14373v1 fatcat:vg5s62ydwnffzivbyrqdu2g5tu

NeRD: Neural Reflectance Decomposition from Image Collections [article]

Mark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron, Ce Liu, Hendrik P.A. Lensch
2021 arXiv   pre-print
We propose a neural reflectance decomposition (NeRD) technique that uses physically-based rendering to decompose the scene into spatially varying BRDF material properties.  ...  Decomposing a scene into its shape, reflectance, and illumination is a challenging but important problem in computer vision and graphics.  ...  This problem is often referred to as inverse rendering [26, 43] , where shape and material properties are estimated from a set of images, e.g., representing the surface properties as spatially-varying  ... 
arXiv:2012.03918v4 fatcat:mueqzzmffncftkd2d73s5fwnya

Reflectance from Images: A Model-Based Approach for Human Faces

M. Fuchs, V. Blanz, H. Lensch, H.-P. Seidel
2005 IEEE Transactions on Visualization and Computer Graphics  
Based on a morphable face model, the system estimates the 3D shape and establishes point-to-point correspondence across images taken from different viewpoints and across different individuals' faces.  ...  We apply analytical BRDF models to express the reflectance properties of each region and we estimate their parameters in a least-squares fit from the image data.  ...  Fig. 11 . 11 Rendered at novel pose and lighting, the images on the left and right show shapes and spatially varying Cook-Torrance BRDFs of two individuals.  ... 
doi:10.1109/tvcg.2005.47 pmid:15868829 fatcat:ffrioum26rc3bbdesiwfsvuouq

BRDF-Reconstruction in Photogrammetry Studio Setups

Matthias Innmann, Jochen Susmuth, Marc Stamminger
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
varying surface reflectance properties and its diffuse albedo.  ...  and detailed geometry.  ...  Acknowledgments We thank Falko Matern for serving as a model for the UPPER BODY scene and Frank Zwick (optimission.de) for capturing and processing the datasets.  ... 
doi:10.1109/wacv45572.2020.9093320 dblp:conf/wacv/InnmannSS20 fatcat:qmkq7yltmrforo6o3qeqc2yyti

Deep Polarization Imaging for 3D shape and SVBRDF Acquisition [article]

Valentin Deschaintre, Yiming Lin, Abhijeet Ghosh
2021 arXiv   pre-print
We present a novel method for efficient acquisition of shape and spatially varying reflectance of 3D objects using polarization cues.  ...  polarization imaging with deep learning to achieve high quality estimate of 3D object shape (surface normals and depth) and SVBRDF using single-view polarization imaging under frontal flash illumination  ...  Acknowledgments This work was supported by an EPSRC Early Career Fellowship (EP/N006259/1) and a hardware donation from Nvidia.  ... 
arXiv:2105.02875v1 fatcat:buuvtovhjrbhvdcu6b7ngqirxy

Principles of appearance acquisition and representation

Tim Weyrich, Jason Lawrence, Hendrik Lensch, Szymon Rusinkiewicz, Todd Zickler
2008 ACM SIGGRAPH 2008 classes on - SIGGRAPH '08  
Adding two spatial dimensions to the four directional dimensions of the BRDF leads us to the six-dimensional Spatially-Varying BRDF.  ...  Spatially-varying Reflectance: SVBRDF Next we allow spatial variation in the reflectance function, which increases the dimension by two.  ...  This shows clearly that spatial BRDF variance is an important aspect of facial appearance.  ... 
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  
Adding two spatial dimensions to the four directional dimensions of the BRDF leads us to the six-dimensional Spatially-Varying BRDF.  ...  Spatially-varying Reflectance: SVBRDF Next we allow spatial variation in the reflectance function, which increases the dimension by two.  ...  This shows clearly that spatial BRDF variance is an important aspect of facial appearance.  ... 
doi:10.1561/0600000022 fatcat:7dro6xcvz5hotdxmr7yvvkvr3y

BRDF Estimation of Complex Materials with Nested Learning [article]

Raquel Vidaurre, Dan Casas, Elena Garces, Jorge Lopez-Moreno
2018 arXiv   pre-print
We propose a novel method that predicts the model parameters of an artist-friendly, physically-based BRDF, from only two low-resolution shots of the material.  ...  The estimation of the optical properties of a material from RGB-images is an important but extremely ill-posed problem in Computer Graphics.  ...  This paper makes the following contributions: • A method that estimates the parameters of an anisotropic BRDF from two shots of the material at 30 • and 90 • degrees. • A hybrid deep learning architecture  ... 
arXiv:1811.09131v1 fatcat:4eiobhkydndrtnku5r7bzmc7ai
« Previous Showing results 1 — 15 out of 485 results