Pooling spike neural network for fast rendering in global illumination

Constantin, Joseph; Bigand, André; Constantin, Ibtissam

doi:10.1007/s00521-018-3941-z

Cited by 4 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 9 shows the number of parameters needed for each model and the times in seconds needed for learning and testing on any block of the

resolution scene. A comparative study based on time complexity between this model and the pooling spike neural network defined in our previous research [ 7 ] shows that the testing time for the pooling spike neural network on the same number of sub-images is equal to 0.01 s; however, it is equal to 0.008 s for the deep active semi-supervised model.…”

Section: Resultsmentioning

confidence: 99%

“…These features are then introduced to a new prediction model which is trained from scratch. In order to extract the noise features, we took the convolution base of a previously trained network [ 7 ], ran the data on it, and trained a new prediction model on top of the output. The network was designed using twelve convolution layers of depth and spread equal to one [ 41 , 42 , 43 ] (see Table 2 ).…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…Machine learning algorithms have provided models for accelerating global illumination rendering by detecting stochastic noise [ 7 , 8 , 9 ]. Some of these models used support vector machine (SVM) and relevance vector machine (RVM) to train the network with labeled data images [ 8 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

“…Some of these models used support vector machine (SVM) and relevance vector machine (RVM) to train the network with labeled data images [ 8 , 9 ]. Another model used a deep spike neural network with a clustering dynamic algorithm for the training images [ 7 ]. The main idea behind these techniques is to detect the increasing quality of images by estimating decreasing noise level using noise attributes.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

On the Use of Deep Active Semi-Supervised Learning for Fast Rendering in Global Illumination

Constantin

Bigand

2020

J. Imaging

Self Cite

View full text Add to dashboard Cite

Convolution neural networks usually require large labeled data-sets to construct accurate models. However, in many real-world scenarios, such as global illumination, labeling data are a time-consuming and costly human intelligent task. Semi-supervised learning methods leverage this issue by making use of a small labeled data-set and a larger set of unlabeled data. In this paper, our contributions focus on the development of a robust algorithm that combines active and deep semi-supervised convolution neural network to reduce labeling workload and to accelerate convergence in case of real-time global illumination. While the theoretical concepts of photo-realistic rendering are well understood, the increased need for the delivery of highly dynamic interactive content in vast virtual environments has increased recently. Particularly, the quality measure of computer-generated images is of great importance. The experiments are conducted on global illumination scenes which contain diverse distortions. Compared with human psycho-visual thresholds, the good consistency between these thresholds and the learning models quality measures can been seen. A comparison has also been made with SVM and other state-of-the-art deep learning models. We do transfer learning by running the convolution base of these models over our image set. Then, we use the output features of the convolution base as input to retrain the parameters of the fully connected layer. The obtained results show that our proposed method provides promising efficiency in terms of precision, time complexity, and optimal architecture.

show abstract

“…Table 9 shows the number of parameters needed for each model and the times in seconds needed for learning and testing on any block of the

Section: Resultsmentioning

confidence: 99%

Section: The Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On the Use of Deep Active Semi-Supervised Learning for Fast Rendering in Global Illumination

Constantin

Bigand

2020

J. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although STDP is able to train spiking neuron to detect spike pattern, however it is difficult to recognize diagnostic features. In previous work, we developed a Pooling Spike Neural Network with a dynamic clustering algorithm based on the Perceptron based Spiking Neuron learning rule (PBSNLR) to solve the global illumination algorithm problem [25]. However, the proposed model is very computationally expensive as it requires a variety of filtering techniques to detect the 26 attributes of the stochastic noise.…”

Section: Introductionmentioning

confidence: 99%

Heterogeneous Regularization for Fast Rendering using Deep Spike Neural Network

Constantin

Dornaika

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

In real-time rendering, images are computed at a very high speed to make them look like the real scenes. Speed and interactivity play an important role in real-time rendering. However, computing indirect lighting in real time is a major challenge because it is very computationally intensive. To be used in video movies, the rendering program must run very fast and the video engine must operate at a constant frame rate. The images must be noise-free and the animations must remain stable without temporal artifacts. Global lighting in videos is still a real challenge. The rendering program must calculate the entire light exchange between the surfaces of a virtual 3D scene. Offline techniques are capable of rendering photo-realistic images, but none of these algorithms is capable of generating images in real time with a high number of frames per second. In this work, a Deep Spiking Neural Network with Heterogeneous Regularization learning technique is proposed with the aim of building a more biologically plausible network to evaluate the amount of noise and find a stopping criterion for fast realistic illumination. The idea is to improve learning performance by extracting the most relevant features with a deep spiking neural network to achieve high rendering quality. We used a new objective function composed from a supervised term and an unsupervised term. The supervised term enforces the fitting term between the predicted labels and the known labels. The unsupervised term imposes the smoothness of the predicted labels. The experiments was performed on scenes with global illumination containing different image distortions. The proposed model is also compared with the human visual system and other state-of-the-art models. Results show better performance and advantages in terms of efficiency, an increasingly biologically plausible network, and ease of implementation in Neuromorphic hardware.

show abstract