119,726 Hits in 5.2 sec

Adaptive rendering with non-local means filtering

Fabrice Rousselle, Claude Knaus, Matthias Zwicker
2012 ACM Transactions on Graphics  
First, we adaptively distribute samples in the image plane. Second, we denoise the image using a non-linear filter.  ...  Abstract We propose a novel approach for image space adaptive sampling and filtering in Monte Carlo rendering. We use an iterative scheme composed of three steps.  ...  In summary we make the following contributions: • An adaptive rendering framework based on non-local means filtering.  ... 
doi:10.1145/2366145.2366214 fatcat:sylgvcofgrg2hdpjf77ukfuqba

SURE-based optimization for adaptive sampling and reconstruction

Tzu-Mao Li, Yu-Ting Wu, Yung-Yu Chuang
2012 ACM Transactions on Graphics  
Abstract We apply Stein's Unbiased Risk Estimator (SURE) to adaptive sampling and reconstruction to reduce noise in Monte Carlo rendering.  ...  With SURE, we are able to use kernels (cross bilateral filters in this case) that are more effective than GEM's isotropic Gassians.  ...  We would like to thank the anonymous reviewers for their valuable comments and the creators of the models used in this paper: airplane (Pedro Caparros), Ferrari (Render-Here), buildings, street cones (  ... 
doi:10.1145/2366145.2366213 fatcat:poivggmmrjgenbw7urxbu77mvu

Hdr Cfa Image Rendering

David Alleysson, Laurence Meylan, Sabine Susstrunk
2006 Zenodo  
Adaptive non-linearity We use an adaptive non-linearity that allows adapting the level of the signal with a non linear mapping.  ...  The horizontal cell filtering is applied and that output is used to calculate the local parameter of the non-linear function.  ... 
doi:10.5281/zenodo.52656 fatcat:pabsuzgwffcsznhet65ssxn57a

Non-Local Image Reconstruction for Efficient Computation of Synthetic Bidirectional Texture Functions

K. Schröder, R. Klein, A. Zinke
2013 Computer graphics forum (Print)  
This is done in a process we call non-local image reconstruction, which has been inspired by non-local means filtering.  ...  From left to right: Our method using 1 sample per pixel (spp) and non-local image reconstruction for BTF generation; unbiased Monte Carlo reference with 128 spp; unbiased Monte Carlo path tracing result  ...  .: Bayesian non-local means filter, image redundancy and adaptive dictionaries for noise removal.  ... 
doi:10.1111/cgf.12144 fatcat:s2ff7nwqijbg7pbdolhtbgy6ma

Recent Advances in Adaptive Sampling and Reconstruction for Monte Carlo Rendering

M. Zwicker, W. Jarosz, J. Lehtinen, B. Moon, R. Ramamoorthi, F. Rousselle, P. Sen, C. Soler, S.-E. Yoon
2015 Computer graphics forum (Print)  
They typically estimate the errors of several reconstruction filters, and select the best filter locally to minimize error.  ...  However, the visual quality of rendered images often suffers from estimator variance, which appears as visually distracting noise.  ...  Finally, we are grateful to the Monte Carlo rendering research community, in particular those working in adaptive sampling and reconstruction whose work we discuss here.  ... 
doi:10.1111/cgf.12592 fatcat:yejby37itfeg5mzo4w5adtnjxa

Silencing the noise onElysium

Luke Goddard
2014 ACM SIGGRAPH 2014 Talks on - SIGGRAPH '14  
We present a new solution to the common issue of ray-traced noise, drastically reducing render times by expanding the use of a temporal filter to attenuate the weighting of a non-local means algorithm  ...  Finally, using information on the sample's range and variance, we perform a process of weighted averages similar to the popular Non-Local Means Algorithm to further improve the result.  ...  with a temporal filter.  ... 
doi:10.1145/2614106.2614116 dblp:conf/siggraph/Goddard14 fatcat:7ptyd5rfnvazbn7pfkmwjzm4qu

Model of retinal local adaptation for the tone mapping of color filter array images

Laurence Meylan, David Alleysson, Sabine Süsstrunk
2007 Optical Society of America. Journal A: Optics, Image Science, and Vision  
Our algorithm provides pleasing results on various images with different scene content and dynamic range.  ...  Second, we introduce a variation of the center/surround class of local tone mapping algorithms, which are known to increase the local contrast of images but tend to create artifacts.  ...  The non-linearities are modeled with a Naka-Rushton function, where the adaptation parameter is an average of the local surround.  ... 
doi:10.1364/josaa.24.002807 pmid:17767249 fatcat:7lhmj5tqazca5mkj2dhaiohaae

General and Robust Error Estimation and Reconstruction for Monte Carlo Rendering

Pablo Bauszat, Martin Eisemann, Elmar Eisemann, Marcus Magnor
2015 Computer graphics forum (Print)  
Abstract Adaptive filtering techniques have proven successful in handling non-uniform noise in Monte-Carlo rendering approaches.  ...  The filter selection is then formulated as a non-local optimization problem, which we solve via graph cuts, to avoid visual artifacts due to inconsistent filter choices.  ...  The freedom to basically use any reconstruction techniques, in combination with our robust error estimator, significantly improves the reconstruction results over state-of-the-art approaches.  ... 
doi:10.1111/cgf.12587 fatcat:rl5hz4qambavhn5fwz246kt3ou

Adaptive Rendering Based on Weighted Local Regression

Bochang Moon, Nathan Carr, Sung-Eui Yoon
2014 ACM Transactions on Graphics  
We derive an error analysis to guide our adaptive sampling process at the local space.  ...  We develop a novel image plane adaptive sampling and reconstruction method based on local regression theory.  ...  For the non-local means (NLM) adaptive rendering [Rousselle et al. 2012 ], we use the CUDA code provided by the authors.  ... 
doi:10.1145/2641762 fatcat:i6ji5eywc5hazoa3zqzwfnqpbi

Adaptive rendering based on weighted local regression

Bochang Moon, Nathan Carr, Sung-Eui Yoon
2014 ACM SIGGRAPH 2014 Talks on - SIGGRAPH '14  
We derive an error analysis to guide our adaptive sampling process at the local space.  ...  We develop a novel image plane adaptive sampling and reconstruction method based on local regression theory.  ...  For the non-local means (NLM) adaptive rendering [Rousselle et al. 2012 ], we use the CUDA code provided by the authors.  ... 
doi:10.1145/2614106.2614160 dblp:conf/siggraph/MoonCY14 fatcat:5f2qszwkqfey5gtbtipuxkv2gy

High dynamic range image rendering with a retinex-based adaptive filter

L. Meylan, S. Susstrunk
2006 IEEE Transactions on Image Processing  
We propose a new method to render high dynamic range images that models global and local adaptation of the human visual system. Our method is based on the centersurround Retinex model.  ...  We show that our method efficiently renders high dynamic range images and we compare our results with the current state of the art.  ...  Left: Non-adaptive filter method. Right: Adaptive filter method. Fig. 9 . 9 Left: Image treated with MSRCR. Right: Image treated with the adaptive filter method.  ... 
doi:10.1109/tip.2006.877312 pmid:16948325 fatcat:xcree4r5k5gh3bowg2waaoolxe

Feature Enhancement using Locally Adaptive Volume Rendering [article]

Stephane Marchesin, Jean-Michel Dischler, Catherine Mongenet
2007 International Workshop on Volume Graphics, Proceedings of the  
In this paper we introduce a new, straightforward rendering technique called locally adaptive volume rendering, that consists in slightly modifying the traditional volume rendering equation in order to  ...  As will be shown by our comparative study with standard volume rendering, this makes our rendering method much more suitable for interactive data exploration at a low extra cost.  ...  Results We have experimented locally adaptive volume rendering with both DVR and additive volume rendering.  ... 
doi:10.2312/vg/vg07/041-048 fatcat:faor4k4dirdgphyq23zp4vj3du

Digital camera workflow for high dynamic range images using a model of retinal processing

Daniel Tamburrino, David Alleysson, Laurence Meylan, Sabine Süsstrunk, Jeffrey M. DiCarlo, Brian G. Rodricks
2008 Digital Photography IV  
This is especially important as our tone mapping operator applies local and global tone corrections, which is usually needed to well render high dynamic scenes.  ...  Our algorithms efficiently process HDR images with different keys and different content.  ...  Filter Sizes: Local Contrast, Sharpening, and Artifacts In the proposed tone mapping algorithm, the non-linearity based on the Naka-Rushton equation is applied twice, with two gaussian filters of spatial  ... 
doi:10.1117/12.767728 dblp:conf/dphoto/TamburrinoAMS08 fatcat:zqws2jh5uvdgdmh2hympp7ye7e

Adaptive Frameless Rendering [article]

Abhinav Dayal, Cliff Woolley, Benjamin Watson, David Luebke
2005 Symposium on Rendering  
We propose an adaptive form of frameless rendering with the potential to dramatically increase rendering speed over conventional interactive rendering approaches.  ...  Without the rigid sampling patterns of framed renderers, sampling and reconstruction can adapt with very fine granularity to spatio-temporal color change.  ...  Acknowledgements Thanks to Greg Humphreys, who created the video, and to Bruce Walter for discussions of the Render Cache.  ... 
doi:10.2312/egwr/egsr05/265-275 fatcat:2g5qrekbrnh3jn6lgqgkpidl7q

A unified scheme for adaptive stroke-based rendering

Hyung W. Kang, Charles K. Chui, Uday K. Chakraborty
2006 The Visual Computer  
We also introduce an 'adaptive bilateral filter' to adaptively guide the curved stroke directions based on the importance map.  ...  Using strokes as the major building blocks, our system optimizes the stroke attributes subject to the desired rendering style.  ...  Fig. 8 shows example adaptive direction maps obtained by our filter with varying kernel size (from Fig. 7(a) ).  ... 
doi:10.1007/s00371-006-0066-7 fatcat:2a6bk4v2vzcvzk6aj73uehubsy
« Previous Showing results 1 — 15 out of 119,726 results