Filters








2,286 Hits in 3.1 sec

Deep Shading: Convolutional Neural Networks for Screen Space Shading

O. Nalbach, E. Arabadzhiyska, D. Mehta, H.-P. Seidel, T. Ritschel
2017 Computer graphics forum (Print)  
In computer vision, convolutional neural networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions  ...  The resulting Deep Shading simulates various screen-space effects at competitive quality and speed while not being programmed by human experts but learned from example images.  ...  (Convolutional) Neural Networks Neural networks are a way of defining powerful non-linear approximations f .  ... 
doi:10.1111/cgf.13225 fatcat:goqmnw7xwjdcbernfyg46is34u

DeepAO: Efficient Screen Space Ambient Occlusion Generation via Deep Network

Dongjiu Zhang, Chuhua Xian, Guoliang Luo, Yunhui Xiong, Chu Han
2020 IEEE Access  
Then, we design an efficient deep neural network for the screen space AO image generation, based on which we further design a Compute Shader Library to compute the shaded AO images.  ...  INDEX TERMS Ambient occlusion, rendering, shading, deep neural network.  ...  [12] introduce a convolution neural network named Deep Shading to learn a mapping from position in camera space and normal to AO shaded image.  ... 
doi:10.1109/access.2020.2984771 fatcat:ji6von45gramfoi3ehq27ce36e

Deep-learning the Latent Space of Light Transport [article]

Pedro Hermosilla and Sebastian Maisch and Tobias Ritschel and Timo Ropinski
2019 arXiv   pre-print
While many previous learning methods have employed 2D convolutional neural networks applied to images, we show for the first time that light transport can be learned directly in 3D.  ...  We suggest a method to directly deep-learn light transport, i. e., the mapping from a 3D geometry-illumination-material configuration to a shaded 2D image.  ...  We would like to acknowledge the NVIDIA Corporation for donating a Quadro P6000 for our training cluster, and Gloria Fackelmann for providing the voice over the supplementary video.  ... 
arXiv:1811.04756v2 fatcat:cjpkvlradra7lf5bma7wfjmnce

Plausible Shading Decomposition For Layered Photo Retouching [article]

Carlo Innamorati, Tobias Ritschel, Tim Weyrich, Niloy J. Mitra
2017 arXiv   pre-print
We perform such a decomposition by learning a convolutional neural network trained using synthetic data.  ...  shading.  ...  The occlusion term O is computed using screen-space occlusion [Ritschel et al. 2009 ].  ... 
arXiv:1701.06507v2 fatcat:oowoduhk7jg4fgx7uetxpvpjeq

Image Colour Prediction using Deep Learning

2020 International journal of recent technology and engineering  
Any image we perceive through a screen is made of three separate channels, R, G, and B. With the help of these three channels; an image comes to colour.  ...  Generative adversarial networks are an unsupervised learning task in machine learning that involves automatically discovering and learning the regularities or patterns in input file to get an output.  ...  We are using the Convolution Neural Framework fit for concealing profoundly differentiating pictures.  ... 
doi:10.35940/ijrte.e5935.038620 fatcat:5kj2gu34hrdanlff7vqkg4lmnm

Object Classification and Detection using Deep Convolution Neural Network Architecture

2020 International journal of recent technology and engineering  
A solid programmed disallowed thing location framework is subsequently ideal for accelerating the screening procedure just as improving the precision of risk identification.  ...  X-Ray security stuff screening frameworks are generally introduced in pretty much every station/air terminal to guarantee open vehicle security.  ...  This positively is useful for Convolutional Neural Network model preparation. II. RELATED WORK Deep convolutional neural network (DCNN) improvements have two expressions.  ... 
doi:10.35940/ijrte.f9834.059120 fatcat:6egijwjlvbaltm3kke7p5fjjlq

Deep Photon Mapping [article]

Shilin Zhu, Zexiang Xu, Henrik Wann Jensen, Hao Su, Ravi Ramamoorthi
2020 arXiv   pre-print
We train a novel deep neural network to predict a kernel function to aggregate photon contributions at shading points.  ...  In this paper, we develop the first deep learning-based method for particle-based rendering, and specifically focus on photon density estimation, the core of all particle-based methods.  ...  in both scene-space particle density estimation and screen-space MC integration.  ... 
arXiv:2004.12069v1 fatcat:fias4l6d5ngdnlxhtgsmwhboke

Deep Reinforcement Learning for Pellet Eating in Agar.io

Nil Ansó, Anton Wiehe, Madalina Drugan, Marco Wiering
2019 Proceedings of the 11th International Conference on Agents and Artificial Intelligence  
The architectures examined are two convolutional Deep Q-networks (DQN) of varying depth and one multilayer perceptron.  ...  This work first investigates how different state representations affect the learning process of a Q-learning algorithm combined with artificial neural networks which are used for representing the Q-function  ...  ACKNOWLEDGMENTS We would like to thank the Center for Information Technology of the University of Groningen for their support and for providing access to the Peregrine high performance computing cluster  ... 
doi:10.5220/0007360901230133 dblp:conf/icaart/AnsoWDW19 fatcat:k5i3z262irb6xegeplfbz2ycpa

Deep Illumination: Approximating Dynamic Global Illumination with Generative Adversarial Network [article]

Manu Mathew Thomas, Angus G. Forbes
2018 arXiv   pre-print
Inspired from recent advancement in image-to-image translation problems using deep generative convolutional networks, we introduce a variant of this network that learns a mapping from Gbuffers (depth map  ...  Our primary contribution is showing that a generative model can be used to learn a density estimation from screen space buffers to an advanced illumination model for a 3D environment.  ...  Another technique called Deep Shading [NAM * 17] uses a convolutional neural network to learn a mapping from screen space buffers to various screen space effects, such as ambient occlusion, indirect light  ... 
arXiv:1710.09834v2 fatcat:qoaxzqus6vewzfaqfenfsyyjym

Classification of Skin Cancer using Deep Learning

Mrs. S. Uma, R. Kavitha, V. Kaviya, V. Monisha, E. Nikhitha
2020 Zenodo  
Right now we have arranged the Benign and Malignant skin disease utilizing convolutional neural network.  ...  , screening patients with centred skin side effects utilizing physician-directed full body skin assessments.  ...  Computers equipped with software based on deep learning, namely convolutional neural networks (CNN) are good at detecting skin cancer than experienced dermatologists.  ... 
doi:10.5281/zenodo.3749685 fatcat:xdwah7v2vbhghi66dp45djik3q

Deep Light Source Estimation for Mixed Reality

Bruno Augusto Dorta Marques, Rafael Rego Drumond, Cristina Nader Vasconcelos, Esteban Clua
2018 Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
We present a deep learning based technique that estimates point light source position from a single color image.  ...  ACKNOWLEDGEMENTS The authors thank Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) for the financial support of this work and Nvidia for providing GPUs.  ...  Deep Convolution Neural Networks represent the state of the art methodology in several tasks related to visual content analysis, and the topology known as Residual Convolution Neural Network (ResNet)  ... 
doi:10.5220/0006724303030311 dblp:conf/grapp/MarquesDVC18 fatcat:or5r5dz32rbrncyjgyya72iu3i

Deep residual learning for denoising Monte Carlo renderings

Kin-Ming Wong, Tien-Tsin Wong
2019 Computational Visual Media  
In this paper, we propose a deep residual learning based method that outperforms both state-of-the-art handcrafted denoisers and learning-based denoisers.  ...  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.  ...  Deep learning for inverse problems Deep convolutional neural networks have demonstrated their great feature extraction power in many difficult image classification problems [30] [31] [32] .  ... 
doi:10.1007/s41095-019-0142-3 fatcat:wcq3vsk7cnce3ome464bh5izse

Deep Manifold Prior [article]

Matheus Gadelha, Rui Wang, Subhransu Maji
2020 arXiv   pre-print
We present a prior for manifold structured data, such as surfaces of 3D shapes, where deep neural networks are adopted to reconstruct a target shape using gradient descent starting from a random initialization  ...  We show that surfaces generated this way are smooth, with limiting behavior characterized by Gaussian processes, and we mathematically derive such properties for fully-connected as well as convolutional  ...  The authors would like to thank Daniel Sheldon for helpful discussions related to Gaussian processes. This work is supported in part by NSF grants #1908669 and #1749833.  ... 
arXiv:2004.04242v1 fatcat:lfqz7abwyfb7jo3uh2mz6m4sse

Sensing Plant Disease Through the Utility of Deep Learning

2020 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
The series of stimulating global Smart phone penetration including up to date advances also latest traits paved the way for deep Learning knowledge practicing public data sets of infected crops and also  ...  healthy plant leaves gathered beneath controlled stipulations, A deep CNN to pick out various crop species including its illnesses(disease) is developed.  ...  Convolutional Neural Networks-After disposing of the noise of the photo it is expected to extorts the feature. We will use a CNN for the file image type.  ... 
doi:10.35940/ijitee.h6463.069820 fatcat:xiruvu62tfa3ffcmijg3dzw724

Deep scattering

Simon Kallweit, Thomas Müller, Brian Mcwilliams, Markus Gross, Jan Novák
2017 ACM Transactions on Graphics  
The descriptor is input to a deep neural network that predicts the radiance function for each shading configuration.  ...  We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks.  ...  ACKNOWLEDGMENTS We thank Delio Vicini for proofreading and helpful discussions, the Stanford 3D Scanning Repository for the Armadillo, Dragon, and StanfordBunny models, and Magnus Wrenninge and the Pixar  ... 
doi:10.1145/3130800.3130880 fatcat:edmisgifgrb53elcurd7n442bi
« Previous Showing results 1 — 15 out of 2,286 results