Filters








311 Hits in 3.5 sec

Kernel-predicting convolutional networks for denoising Monte Carlo renderings

Steve Bako, Thijs Vogels, Brian Mcwilliams, Mark Meyer, Jan NováK, Alex Harvill, Pradeep Sen, Tony Derose, Fabrice Rousselle
2017 ACM Transactions on Graphics  
We conclude by analyzing various components of our architecture and identify areas of further research in deep learning for MC denoising.  ...  networks on production data and observe improvements over state-of-theart MC denoisers, showing that our methods generalize well to a variety of scenes.  ...  ACKNOWLEDGMENTS We gratefully thank John Halstead for generating the Finding Dory training data and Andreas Krause for helpful discussions.  ... 
doi:10.1145/3072959.3073708 fatcat:tgs6xqvgmncefopnztg6c2bbx4

DGAN-KPN: Deep Generative Adversarial Network and Kernel Prediction Network for Denoising MC Renderings

Ahmed Mustafa Taha Alzbier, Chunyi Chen
2022 Symmetry  
Then, the prediction kernel and the preliminarily denoised rendered image is sent to the image reconstruction model for reconstruction, and the prediction kernel is applied to the preliminarily denoised  ...  and finally generates a prediction kernel for each pixel.  ...  In addition, the denoising effects of the data rendered by multiple renderers showed that the network model of this paper had a relatively good generalization ability and a good adaptability to the rendering  ... 
doi:10.3390/sym14020395 fatcat:igyh45t4rva7dbxu3rvi6dadwa

A detail preserving neural network model for Monte Carlo denoising

Weiheng Lin, Beibei Wang, Lu Wang, Nicolas Holzschuch
2020 Computational Visual Media  
The network predicts kernels which are then applied to the noisy input.  ...  Many Monte Carlo denoising methods rely on deep learning: they use convolutional neural networks to learn the relationship between noisy images and reference images, using auxiliary features such as position  ...  Kernel prediction convolutional network Origins Bako et al. proposed the first CNN based Monte Carlo denoising method. They decouple the rendered output into diffuse and specular components.  ... 
doi:10.1007/s41095-020-0167-7 fatcat:cozemwjkkzbwdc2hkwlzyalwxe

Real‐time Monte Carlo Denoising with Weight Sharing Kernel Prediction Network

Hangming Fan, Rui Wang, Yuchi Huo, Hujun Bao
2021 Computer graphics forum (Print)  
Recently, kernel-prediction methods use a neural network to predict each pixel's filtering kernel and have shown a great potential to remove Monte Carlo noise.  ...  This paper expands the kernel-prediction method and proposes a novel approach to denoise very low spp (e.g., 1-spp) Monte Carlo path traced images at real-time frame rates.  ...  real-time kernel prediction Monte Carlo denoising method.  ... 
doi:10.1111/cgf.14338 fatcat:2nky2b3ywrfphoemacddqdb77m

Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool [article]

Tiange Xiang, Hongliang Yuan, Haozhi Huang, Yujin Shi
2021 arXiv   pre-print
Monte Carlo path tracer renders noisy image sequences at low sampling counts.  ...  In this paper, we tackle the problems in Monte Carlo rendering by proposing a two-stage denoiser based on the adaptive sampling strategy.  ...  Related Works Denoising for Monte Carlo Rendering Denoiser for Monte Carlo path tracer enables the renderer to operate in a low sampling count environment without an apparent loss on image quality, saving  ... 
arXiv:2103.16115v1 fatcat:zy3a3xoxsndixf6xnm3cbpedji

DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering [article]

Xin Yang, Wenbo Hu, Dawei Wang, Lijing Zhao, Baocai Yin, Qiang Zhang, Xiaopeng Wei, Hongbo Fu
2019 arXiv   pre-print
Denoising Monte Carlo rendering is different from natural image denoising since inexpensive by-products (feature buffers) can be extracted in the rendering stage.  ...  However, these feature buffers also contain redundant information, which makes Monte Carlo denoising different from natural image denoising.  ...  We propose a deep Dual-Encoder network for denoising Monte Carlo rendering to produce high quality images.  ... 
arXiv:1905.03908v1 fatcat:65sdtdfmxvdjvkmcroysjh7ali

Sample-based Monte Carlo denoising using a kernel-splatting network

Michaël Gharbi, Tzu-Mao Li, Miika Aittala, Jaakko Lehtinen, Frédo Durand
2019 ACM Transactions on Graphics  
We present the first convolutional network that can learn to denoise Monte Carlo renderings directly from the samples.  ...  Denoising has proven to be useful to efficiently generate high-quality Monte Carlo renderings.  ...  CONCLUSION We propose a new convolutional neural network for denoising Monte Carlo renderings.  ... 
doi:10.1145/3306346.3322954 fatcat:guikcr2fefc4xolmktbo5yei4m

Real-time Monte Carlo Denoising with the Neural Bilateral Grid

Xiaoxu Meng, Quan Zheng, Amitabh Varshney, Gurprit Singh, Matthias Zwicker
2020 Eurographics Symposium on Rendering  
Real-time denoising for Monte Carlo rendering remains a critical challenge with regard to the demanding requirements of both high fidelity and low computation time.  ...  In this paper, we propose a novel and practical deep learning approach to robustly denoise Monte Carlo images rendered at sampling rates as low as a single sample per pixel (1-spp).  ...  Monte Carlo rendering.  ... 
doi:10.2312/sr.20201133 dblp:conf/rt/MengZVSZ20 fatcat:qpzyz3eihfgmfmp6ko7zgbtmhy

Fast Reconstruction for Monte Carlo Rendering Using Deep Convolutional Networks

Xin Yang, Dawei Wang, Wenbo Hu, Lijing Zhao, Xinglin Piao, Dongsheng Zhou, Qiang Zhang, Baocai Yin, Xiaopeng Wei
2018 IEEE Access  
INDEX TERMS Monte Carlo rendering, denoise, deep learning, HDR normalization.  ...  Denoising the Monte Carlo (MC) rendering images is different from denoising the natural images since low-sampled MC renderings have a higher noise level and there are inexpensive by-products (e.g., feature  ...  ACKNOWLEDGEMENT The authors would like to thank the anonymous reviewers for the insightful and constructive comments.  ... 
doi:10.1109/access.2018.2886005 fatcat:uiv6bgmvpngqxir45izlgj6z4e

Fast Monte Carlo Rendering via Multi-Resolution Sampling [article]

Qiqi Hou, Zhan Li, Carl S Marshall, Selvakumar Panneer, Feng Liu
2021 arXiv   pre-print
Our experiments show that our hybrid rendering algorithm is significantly faster than the state-of-the-art Monte Carlo denoising methods while rendering high-quality images when tested on both our own  ...  In this paper, we present a hybrid rendering method to speed up Monte Carlo rendering algorithms.  ...  Bako et al. extended this method by employing filters with spatially adaptive kernels to denoise Monte Carlo renderings [2] .  ... 
arXiv:2106.12802v1 fatcat:qmk243d3v5c4dmmtlgfsyybrhq

Deep convolutional reconstruction for gradient-domain rendering

Markus Kettunen, Erik Härkönen, Jaakko Lehtinen
2019 ACM Transactions on Graphics  
Drawing on the power of modern convolutional neural networks, we propose a novel reconstruction method for gradient-domain rendering.  ...  Our results significantly improve the quality obtained from gradientdomain path tracing, allowing it to overtake state-of-the-art comparison techniques that denoise traditional Monte Carlo samplings.  ...  for converting many of them to Mitsuba.  ... 
doi:10.1145/3306346.3323038 fatcat:5d3alsh4hneqzgoiasg6myyldi

Deep residual learning for denoising Monte Carlo renderings

Kin-Ming Wong, Tien-Tsin Wong
2019 Computational Visual Media  
Learning-based techniques have recently been shown to be effective for denoising Monte Carlo rendering methods. However, there remains a quality gap to state-of-the-art handcrafted denoisers.  ...  We have evaluated our method on unseen images created by a different renderer. Consistently superior quality denoising is obtained in all cases.  ...  In short, our contributions are: • A deep learning based single image denoising method for Monte Carlo rendering.  ... 
doi:10.1007/s41095-019-0142-3 fatcat:wcq3vsk7cnce3ome464bh5izse

A survey on deep learning-based Monte Carlo denoising

Yuchi Huo, Sung-eui Yoon
2021 Computational Visual Media  
Recent years have seen increasing attention and significant progress in denoising MC rendering with deep learning, by training neural networks to reconstruct denoised rendering results from sparse MC samples  ...  AbstractMonte Carlo (MC) integration is used ubiquitously in realistic image synthesis because of its flexibility and generality.  ...  Fig. 1 1 Deep learning-based Monte Carlo denoising method trains a neural network to reduce Monte Carlo noise in input images. Reproduced with permission from Ref. [9] , c Author 2018.  ... 
doi:10.1007/s41095-021-0209-9 fatcat:pki3mbbpw5fjxf6oaphcnlto4a

Deep Radiance Caching: Convolutional Autoencoders Deeper in Ray Tracing [article]

Giulio Jiang, Bernhard Kainz
2020 arXiv   pre-print
Caching (DRC), an efficient variant of Radiance Caching utilizing Convolutional Autoencoders for rendering global illumination.  ...  CPU rendering for maximum accessibility.  ...  Kernel-predicting convolutional networks for denoising Monte Carlo renderings [16] and the recent extension Denoising with Kernel Prediction and Asymmetric Loss Functions [17] improve denoising networks  ... 
arXiv:1910.02480v2 fatcat:tmikya7qdvarvbps736z3usnw4

Extension: Adaptive Sampling with Implicit Radiance Field [article]

Yuchi Huo
2022 arXiv   pre-print
Other extended contents: Deep Learning-Based Monte Carlo Noise Reduction By training a neural network denoiser through offline learning, it can filter noisy Monte Carlo rendering results into high-quality  ...  guiding Monte Carlo sampling.  ... 
arXiv:2202.00855v3 fatcat:iqyx2le56ramdkqqwy6pwnpeim
« Previous Showing results 1 — 15 out of 311 results