scholarly journals NeRF

2022 ◽  
Vol 65 (1) ◽  
pp. 99-106
Author(s):  
Ben Mildenhall ◽  
Pratul P. Srinivasan ◽  
Matthew Tancik ◽  
Jonathan T. Barron ◽  
Ravi Ramamoorthi ◽  
...  
Keyword(s):  
Volume Rendering ◽  
State Of The Art ◽  
Spatial Location ◽  
Volume Density ◽  
View Synthesis ◽  
Complex Scenes ◽  
Complicated Geometry ◽  
Fully Connected ◽  
Sparse Set ◽  
Rendering Techniques

We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene using a fully connected (nonconvolutional) deep network, whose input is a single continuous 5D coordinate (spatial location ( x , y , z ) and viewing direction ( θ, ϕ )) and whose output is the volume density and view-dependent emitted radiance at that spatial location. We synthesize views by querying 5D coordinates along camera rays and use classic volume rendering techniques to project the output colors and densities into an image. Because volume rendering is naturally differentiable, the only input required to optimize our representation is a set of images with known camera poses. We describe how to effectively optimize neural radiance fields to render photorealistic novel views of scenes with complicated geometry and appearance, and demonstrate results that outperform prior work on neural rendering and view synthesis.

Identification of Brain Tumors using Volume rendering Techniques

2021 ◽  
Author(s):  
K.Sudha Rani ◽  
K.Mani kumari ◽  
T. Nireekshna ◽  
D.V. Shobana ◽  
N. Kavitha ◽  
...  
Keyword(s):  
Brain Tumors ◽  
Volume Rendering ◽  
Rendering Techniques

Full Body Virtual Autopsies using a State-of-the-art Volume Rendering Pipeline

2006 ◽  
Vol 12 (5) ◽  
pp. 869-876 ◽  
Author(s):  
Patric Ljung ◽  
Calle Winskog ◽  
Anders Persson ◽  
Claes Lundstrom ◽  
Anders Ynnerman
Keyword(s):  
Volume Rendering ◽  
State Of The Art ◽  
Rendering Pipeline ◽  
Full Body

Dangerous Scenes Recognition During Hoisting Based on Faster Region-Based Convolutional Neural Network

2018 ◽  
Author(s):  
Hongguo Su ◽  
Mingyuan Zhang ◽  
Shengyuan Li ◽  
Xuefeng Zhao
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
State Of The Art ◽  
Spatial Location ◽  
Average Precision ◽  
Practical Applications ◽  
Security Enhancement ◽  
Human Interactions

In the last couple of years, advancements in the deep learning, especially in convolutional neural networks, proved to be a boon for the image classification and recognition tasks. One of the important practical applications of object detection and image classification can be for security enhancement. If dangerous objects or scenes can be identified automatically, then a lot of accidents can be prevented. For this purpose, in this paper we made use of state-of-the-art implementation of Faster Region-based Convolutional Neural Network (Faster R-CNN) based on the monitoring video of hoisting sites to train a model to detect the dangerous object and the worker. By extracting the locations of them, object-human interactions during hoisting, mainly for changes in their spatial location relationship, can be understood whereby estimating whether the scene is safe or dangerous. Experimental results showed that the pre-trained model achieved good performance with a high mean average precision of 97.66% on object detection and the proposed method fulfilled the goal of dangerous scenes recognition perfectly.

Fast Volume Rendering Techniques for 3D Reconstruction of Geological Objects

2012 ◽  
Vol 182-183 ◽  
pp. 1343-1346
Author(s):  
De Wen Seng ◽  
Da Qing Li
Keyword(s):  
3D Reconstruction ◽  
Volume Rendering ◽  
Spatial Data ◽  
Real Data ◽  
Tree Structure ◽  
Marching Cubes ◽  
Geological Data ◽  
Iron Mine ◽  
Effectiveness And Efficiency ◽  
Rendering Techniques

The procedure of volume rendering techniques is introduced. The principles and methods of two kinds of different volume rendering techniques of 3D spatial data are discussed. Application of Marching Cubes (MC) algorithm in the modeling of geological objects is given. This algorithm is modified and improved in several aspects. The asymptotic decider algorithm is employed to solve the ambiguity problem and oct-tree structure is used to reduce the number of polygons generated, which will increases the efficiency of the algorithm. The improved algorithm is applied to real geological data obtained from an iron mine in China. Real data derived from an iron mine of China demonstrates the effectiveness and efficiency of the system and the algorithms.

Volumenvisualisierung auf handelsüblicher Grafik-Hardware (Volume Rendering Techniques for General Purpose Graphics Hardware)

2005 ◽  
Vol 47 (1) ◽  
Author(s):  
Christof Rezk Salama
Keyword(s):  
Volume Rendering ◽  
General Purpose ◽  
Graphics Hardware ◽  
Rendering Techniques

AbstractTechniken der Volumenvisualisierung werden zur räumlichen Darstellung dreidimensionaler Skalarfelder benötigt, wie sie beispielsweise in der Medizin in Form von tomografischen Daten entstehen. Diese Arbeit beschäftigt sich mit Ansätzen, hochqualitative Bilder solcher Volumendaten in Echtzeit mithilfe handelsüblicher Grafikkarten zu erzeugen.

scholarly journals Edge-Nodes Representation Neural Machine for Link Prediction

Algorithms ◽  
2019 ◽  
Vol 12 (1) ◽  
pp. 12 ◽  
Author(s):  
Guangluan Xu ◽  
Xiaoke Wang ◽  
Yang Wang ◽  
Daoyu Lin ◽  
Xian Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Formation Mechanism ◽  
Link Prediction ◽  
State Of The Art ◽  
Prediction Methods ◽  
Topological Features ◽  
Novel Method ◽  
Fully Connected ◽  
Two Sides

Link prediction is a task predicting whether there is a link between two nodes in a network. Traditional link prediction methods that assume handcrafted features (such as common neighbors) as the link’s formation mechanism are not universal. Other popular methods tend to learn the link’s representation, but they cannot represent the link fully. In this paper, we propose Edge-Nodes Representation Neural Machine (ENRNM), a novel method which can learn abundant topological features from the network as the link’s representation to promote the formation of the link. The ENRNM learns the link’s formation mechanism by combining the representation of edge and the representations of nodes on the two sides of the edge as link’s full representation. To predict the link’s existence, we train a fully connected neural network which can learn meaningful and abundant patterns. We prove that the features of edge and two nodes have the same importance in link’s formation. Comprehensive experiments are conducted on eight networks, experiment results demonstrate that the method ENRNM not only exceeds plenty of state-of-the-art link prediction methods but also performs very well on diverse networks with different structures and characteristics.

scholarly journals Deep-learning-based macro-pixel synthesis and lossless coding of light field images

2019 ◽  
Vol 8 ◽  
Author(s):  
Ionut Schiopu ◽  
Adrian Munteanu
Keyword(s):  
Light Field ◽  
State Of The Art ◽  
View Synthesis ◽  
Base Layer ◽  
Synthesis Process ◽  
Enhancement Layer ◽  
Novel Approach ◽  
Average Improvement ◽  
Lossless Coding ◽  
One Step

Abstract This paper proposes a novel approach for lossless coding of light field (LF) images based on a macro-pixel (MP) synthesis technique which synthesizes the entire LF image in one step. The reference views used in the synthesis process are selected based on four different view configurations and define the reference LF image. This image is stored as an array of reference MPs which collect one pixel from each reference view, being losslessly encoded as a base layer. A first contribution focuses on a novel network design for view synthesis which synthesizes the entire LF image as an array of synthesized MPs. A second contribution proposes a network model for coding which computes the MP prediction used for lossless encoding of the remaining views as an enhancement layer. Synthesis results show an average distortion of 29.82 dB based on four reference views and up to 36.19 dB based on 25 reference views. Compression results show an average improvement of 29.9% over the traditional lossless image codecs and 9.1% over the state-of-the-art.

scholarly journals A perceptive evaluation of volume rendering techniques

2009 ◽  
Vol 5 (4) ◽  
pp. 1-24 ◽  
Author(s):  
Christian Boucheny ◽  
Georges-Pierre Bonneau ◽  
Jacques Droulez ◽  
Guillaume Thibault ◽  
Stephane Ploix
Keyword(s):  
Volume Rendering ◽  
Rendering Techniques
Sign in / Sign up

Export Citation Format

Share Document