Filters








241 Hits in 3.8 sec

Smooth Reconstruction and Compact Representation of Reflectance Functions for Image-based Relighting [article]

Vincent Masselus, Pieter Peers, Philip Dutré, Yves D. Willemsy
2004 Symposium on Rendering  
In this paper we present a new method to reconstruct reflectance functions for image-based relighting.  ...  Additionally we present a compact representation of the reconstructed reflectance functions.  ...  Acknowledgments We would like to thank Frank Suykens for proofreading the paper. This work was partially supported by FWO Grant #G.0354.00 and K.U.Leuven Grant #OT/01-34.  ... 
doi:10.2312/egwr/egsr04/287-298 fatcat:4r3xjd3sr5g37o5glotm6j3mue

Dense Photometric Stereo: A Markov Random Field Approach

Tai-Pang Wu, Kam-Lun Tang, Chi-Keung Tang, Tien-Tsin Wong
2006 IEEE Transactions on Pattern Analysis and Machine Intelligence  
With the reconstructed surface, an inverse process, known as relighting in computer graphics, is proposed to synthesize novel images of the given scene under user-specified light source and direction.  ...  The input is a dense set of noisy photometric images, conveniently captured by using a very simple set-up consisting of a digital video camera, a reflective mirror sphere, and a handheld spotlight.  ...  ACKNOWLEDGMENTS The authors would like to thank the associate editor and all of the reviewers for their thorough and constructive suggestions which were instrumental in improving the quality of the final  ... 
doi:10.1109/tpami.2006.224 pmid:17063687 fatcat:iwk5lh3msnbsfflsnd47goiwoe

Neural Ray-Tracing: Learning Surfaces and Reflectance for Relighting and View Synthesis [article]

Julian Knodt, Joe Bartusek, Seung-Hwan Baek, Felix Heide
2021 arXiv   pre-print
We validate the proposed approach for scene editing, relighting and reflectance estimation learned from synthetic and captured views on a subset of NeRV's datasets.  ...  The method outperforms NeRV for relighting under known lighting conditions, and produces realistic reconstructions for relit and edited scenes.  ...  This allows for effective reconstruction of smooth shapes in a scene as shown in Figure 4 .  ... 
arXiv:2104.13562v2 fatcat:bgy25vm77jaudfcx4l4ftvwvfq

Cosine Lobe Based Relighting from Gradient Illumination Photographs

Graham Fyffe, Cyrus A. Wilson, Paul Debevec
2009 2009 Conference for Visual Media Production  
We present an image-based method for relighting a scene by analytically fitting a cosine lobe to the reflectance function at each pixel, based on gradient illumination photographs.  ...  We explore two cosine lobe reflectance functions, both of which allow an analytic fit to the gradient conditions.  ...  We would also like to thank Monica Nichelson, Bill Swartout, and Randall Hill for their support and assistance with this work.  ... 
doi:10.1109/cvmp.2009.18 fatcat:rbizye7ntfbdnc4yk2j6hztouy

Cosine lobe based relighting from gradient illumination photographs

Graham Fyffe
2009 SIGGRAPH '09: Posters on - SIGGRAPH '09  
We present an image-based method for relighting a scene by analytically fitting a cosine lobe to the reflectance function at each pixel, based on gradient illumination photographs.  ...  We explore two cosine lobe reflectance functions, both of which allow an analytic fit to the gradient conditions.  ...  We would also like to thank Monica Nichelson, Bill Swartout, and Randall Hill for their support and assistance with this work.  ... 
doi:10.1145/1599301.1599381 dblp:conf/siggraph/Fyffe09 fatcat:ckzkzv2pdne2tmicfcyqunwimm

Neural reflectance transformation imaging

Tinsae G. Dulecha, Filippo A. Fanni, Federico Ponchio, Fabio Pellacini, Andrea Giachetti
2020 The Visual Computer  
In this paper, we present NeuralRTI, a framework for pixel-based encoding and relighting of RTI data.  ...  The solution used in practical applications consists of creating "relightable images" by approximating the pixel information with a function of the light direction, encoded with a small number of parameters  ...  [17] combined principal component analysis (PCA)-based compression of the image stack and Radial Basis Function (RBF) interpolation in the light direction space to provide an efficient relightable image  ... 
doi:10.1007/s00371-020-01910-9 fatcat:q5rhmh3uvrccvk6h3klwm3odjm

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
Though recent work has shown that implicit representations can be used to model the radiance field of an object, most of these techniques only enable view synthesis and not relighting.  ...  We demonstrate the potential of the proposed approach with experiments on both synthetic and real datasets, where we are able to obtain high-quality relightable 3D assets from image collections.  ...  Our key technique is an explicit decomposition model for shape, reflectance, and illumination within a NeRFlike coordinate-based neural representation framework [38] .  ... 
arXiv:2012.03918v4 fatcat:mueqzzmffncftkd2d73s5fwnya

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)  
Our method enables plausible reconstruction of relightable dynamic scene models without a complex controlled lighting apparatus, and opens up a path towards relightable performance capture in less constrained  ...  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  ...  Reflectance Estimation and Relighting In the past, a variety of approaches have been proposed for image-based estimation of reflectance models for static scenes.  ... 
doi:10.1111/cgf.12047 fatcat:hsxhjqbjtndrzo3d3twnsp3e3m

Factored time-lapse video

Kalyan Sunkavalli, Wojciech Matusik, Hanspeter Pfister, Szymon Rusinkiewicz
2007 ACM Transactions on Graphics  
The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations.  ...  The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations.  ...  Acknowledgments We would like to thank the anonymous reviewers for their insightful comments and Jennifer Roderick for proofreading the paper.  ... 
doi:10.1145/1239451.1239552 fatcat:t2ub7e2w4nfiln72xacsxhfliq

Factored time-lapse video

Kalyan Sunkavalli, Wojciech Matusik, Hanspeter Pfister, Szymon Rusinkiewicz
2007 ACM SIGGRAPH 2007 papers on - SIGGRAPH '07  
The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations.  ...  The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations.  ...  Acknowledgments We would like to thank the anonymous reviewers for their insightful comments and Jennifer Roderick for proofreading the paper.  ... 
doi:10.1145/1275808.1276504 fatcat:33nwp3nq3fbo5poo4uqux2irsm

Capturing Reflectance - From Theory to Practice [article]

Hendrik P. A. Lensch, Michael Goesele, Gero M¨Uller
2007 Eurographics State of the Art Reports  
In this tutorial we will mainly focus on three different approaches, the first allowing to reconstruct opaque surfaces from a very small set of input images, the second allows for arbitrary surfaces but  ...  under the assumption of distant light sources and the last which allows for relighting an arbitrary scene with arbitrary spatially varying light patterns.  ...  Image-Based Reconstruction of Spatial Appearance and Geometric Detail. ACM Transactions on This paper extends the measurement setup of [14] to anisotropic BRDFs.  ... 
doi:10.2312/egt.20071065 fatcat:vov7vxmgirct3bs72xxcpe5w24

Factored time-lapse video

Kalyan Sunkavalli, Wojciech Matusik, Hanspeter Pfister, Szymon Rusinkiewicz
2007 ACM Transactions on Graphics  
The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations.  ...  Our method is easy to implement, robust, and provides a compact representation with good reconstruction characteristics. We show results using several publicly available time-lapse sequences.  ...  Acknowledgments We would like to thank the anonymous reviewers for their insightful comments and Jennifer Roderick for proofreading the paper.  ... 
doi:10.1145/1276377.1276504 fatcat:5xd2pihwkbdqdbk543oxdx4di4

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

Zhengqin Li, Kalyan Sunkavalli, Manmohan Chandraker
2018 arXiv   pre-print
The framework is trained end-to-end and produces high quality results for a variety of materials.  ...  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.  ...  In some cases, such as the second row of the first column, we observe that even very tight specular lobes are well-estimated, as evident from the lobe's compactness in the relighted image.  ... 
arXiv:1804.05790v1 fatcat:yhpmf3t6ezgr5kmpzvq7mxjihm

High-Quality Reconstruction from Multiview Video Streams

Christian Theobalt, Naveed Ahmed, Gernot Ziegler, Hans-Peter Seidel
2007 IEEE Signal Processing Magazine  
Hans-Peter Seidel (hpseidel@mpi-inf.mpg.de) is the scientific director and chair of the computer graphics group at the Max-Planck-Institut (MPI) Informatik and a professor of computer science at Saarland  ...  He has received grants from a wide range of organizations, including the German National Science Foundation (DFG), the German Federal Government (BMBF), the European Community (EU), NATO, and the German-Israel  ...  The modelbased framework allows for an efficient compaction of even relightable dynamic scene representations, which lends itself to real-time visualization on consumer-grade hardware.  ... 
doi:10.1109/msp.2007.905701 fatcat:b6eactaforblbcvigpfi2marsm

High-Quality Reconstruction from Multiview Video Streams

Christian Theobalt, Naveed Ahmed, Gernot Ziegler, Hans-Peter Seidel
2007 IEEE Signal Processing Magazine  
Hans-Peter Seidel (hpseidel@mpi-inf.mpg.de) is the scientific director and chair of the computer graphics group at the Max-Planck-Institut (MPI) Informatik and a professor of computer science at Saarland  ...  He has received grants from a wide range of organizations, including the German National Science Foundation (DFG), the German Federal Government (BMBF), the European Community (EU), NATO, and the German-Israel  ...  The modelbased framework allows for an efficient compaction of even relightable dynamic scene representations, which lends itself to real-time visualization on consumer-grade hardware.  ... 
doi:10.1109/msp.2007.4317463 fatcat:oszmwupeb5bqrli3cr3ozoll4y
« Previous Showing results 1 — 15 out of 241 results