Abstract
Ambient occlusion ( abbr . AO) plays an important role in realistic rendering applications because AO produces more realistic ambient lighting, which is achieved by calculating the brightness of certain screen parts based on objects’ geometry. However, the baseline computation of AO algorithm is time-consuming, which limits its application for real-time rendering. Currently, most AO algorithms are based on screen space to reduce the computational consumption, which leads to unrealistic results due to the usage of artificial features. To overcome these challenges, in this paper, we first create a well-crafted dataset with the pair of deferred shading buffer data and ground-truth AO shaded images. 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. Our extensive experimental results show that our method achieves competent performance than existing screen space ambient or volumetric ambient based AO methods both in visual quality and efficiency.
Highlights
INTRODUCTIONSSAO-based methods utilize the screen space information, including depth and normal, stored in G buffer to compute the occlusions that are independent from the complexity of scene
To overcome the above limitations, we build our own dataset with both deferred shading buffers and ground truth AO shaded images
We first construct our dataset with pairs of deferred shading buffers and ground truth shaded AO images
Summary
SSAO-based methods utilize the screen space information, including depth and normal, stored in G buffer to compute the occlusions that are independent from the complexity of scene. These methods are extensively used in real-time applications because of the simple implementation and high efficiency. We first create a dataset that contains camera space depth, normal and ground truth AO that can be computed via a ray-trace-based render. We have developed a Compute Shading Library, which is simple, fast and efficient implementation of neural network in game engine This library can be applied to other rendering tasks. The batch size is set to 16, and the leaky-ReLU negative slope is set to 0.01
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
