FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288064690> ?p ?o ?g. }

• W4288064690 endingPage "23123" @default.
• W4288064690 startingPage "23114" @default.
• W4288064690 abstract "Driving simulators play a large role in developing and testing new intelligent vehicle systems. The visual fidelity of the simulation is critical for building vision-based algorithms and conducting human driver experiments. Low visual fidelity breaks immersion for human-in-the-loop driving experiments. Conventional computer graphics pipelines use detailed 3D models, meshes, textures, and rendering engines to generate 2D images from 3D scenes. These processes are labor-intensive, and they do not generate photorealistic imagery. Here we introduce a hybrid generative neural graphics pipeline for improving the visual fidelity of driving simulations. Given a 3D scene, we partially-render only important objects of interest, such as vehicles, and use generative adversarial processes to synthesize the background and the rest of the image. To this end, we propose a novel image formation strategy to form 2D semantic images from 3D scenery consisting of simple object models without textures. These semantic images are then converted into photorealistic RGB images with a state-of-the-art Generative Adversarial Network (GAN) trained on real-world driving scenes. This replaces repetitiveness with randomly generated but photorealistic surfaces. Finally, the partially-rendered and GAN synthesized images are blended with a blending GAN. We show that the photorealism of images generated with the proposed method is more similar to real-world driving datasets such as Cityscapes and KITTI than conventional approaches. This comparison is made using semantic retention analysis and Frechet Inception Distance (FID) measurements." @default.
• W4288064690 created "2022-07-28" @default.
• W4288064690 creator A5027111254 @default.
• W4288064690 creator A5031280652 @default.
• W4288064690 creator A5067003176 @default.
• W4288064690 creator A5088312544 @default.
• W4288064690 date "2022-12-01" @default.
• W4288064690 modified "2023-09-23" @default.
• W4288064690 title "Photorealism in Driving Simulations: Blending Generative Adversarial Image Synthesis With Rendering" @default.
• W4288064690 cites W1798731418 @default.
• W4288064690 cites W183071939 @default.
• W4288064690 cites W1998393535 @default.
• W4288064690 cites W2020664685 @default.
• W4288064690 cites W2079155753 @default.
• W4288064690 cites W2083366168 @default.
• W4288064690 cites W2108598243 @default.
• W4288064690 cites W2115579991 @default.
• W4288064690 cites W2170548555 @default.
• W4288064690 cites W2183341477 @default.
• W4288064690 cites W2340897893 @default.
• W4288064690 cites W2412782625 @default.
• W4288064690 cites W2518945384 @default.
• W4288064690 cites W2584009249 @default.
• W4288064690 cites W2593768305 @default.
• W4288064690 cites W2737258237 @default.
• W4288064690 cites W2811214855 @default.
• W4288064690 cites W2948741662 @default.
• W4288064690 cites W2962793481 @default.
• W4288064690 cites W2962974533 @default.
• W4288064690 cites W2963000559 @default.
• W4288064690 cites W2963073614 @default.
• W4288064690 cites W2963163163 @default.
• W4288064690 cites W2963522749 @default.
• W4288064690 cites W2963527086 @default.
• W4288064690 cites W2963539305 @default.
• W4288064690 cites W2963800363 @default.
• W4288064690 cites W2964024144 @default.
• W4288064690 cites W2964125246 @default.
• W4288064690 cites W2982014123 @default.
• W4288064690 cites W2990173985 @default.
• W4288064690 cites W3000192950 @default.
• W4288064690 cites W3021907900 @default.
• W4288064690 cites W3091109630 @default.
• W4288064690 cites W3098481019 @default.
• W4288064690 cites W3111506700 @default.
• W4288064690 cites W4245933748 @default.
• W4288064690 doi "https://doi.org/10.1109/tits.2022.3193347" @default.
• W4288064690 hasPublicationYear "2022" @default.
• W4288064690 type Work @default.
• W4288064690 citedByCount "0" @default.
• W4288064690 crossrefType "journal-article" @default.
• W4288064690 hasAuthorship W4288064690A5027111254 @default.
• W4288064690 hasAuthorship W4288064690A5031280652 @default.
• W4288064690 hasAuthorship W4288064690A5067003176 @default.
• W4288064690 hasAuthorship W4288064690A5088312544 @default.
• W4288064690 hasBestOaLocation W42880646902 @default.
• W4288064690 hasConcept C113364801 @default.
• W4288064690 hasConcept C115961682 @default.
• W4288064690 hasConcept C119599485 @default.
• W4288064690 hasConcept C121684516 @default.
• W4288064690 hasConcept C127413603 @default.
• W4288064690 hasConcept C154945302 @default.
• W4288064690 hasConcept C173552908 @default.
• W4288064690 hasConcept C205711294 @default.
• W4288064690 hasConcept C21442007 @default.
• W4288064690 hasConcept C2776459999 @default.
• W4288064690 hasConcept C2988773926 @default.
• W4288064690 hasConcept C31487907 @default.
• W4288064690 hasConcept C31972630 @default.
• W4288064690 hasConcept C36464697 @default.
• W4288064690 hasConcept C39890363 @default.
• W4288064690 hasConcept C41008148 @default.
• W4288064690 hasConcept C50644808 @default.
• W4288064690 hasConcept C66629338 @default.
• W4288064690 hasConcept C76155785 @default.
• W4288064690 hasConcept C77660652 @default.
• W4288064690 hasConceptScore W4288064690C113364801 @default.
• W4288064690 hasConceptScore W4288064690C115961682 @default.
• W4288064690 hasConceptScore W4288064690C119599485 @default.
• W4288064690 hasConceptScore W4288064690C121684516 @default.
• W4288064690 hasConceptScore W4288064690C127413603 @default.
• W4288064690 hasConceptScore W4288064690C154945302 @default.
• W4288064690 hasConceptScore W4288064690C173552908 @default.
• W4288064690 hasConceptScore W4288064690C205711294 @default.
• W4288064690 hasConceptScore W4288064690C21442007 @default.
• W4288064690 hasConceptScore W4288064690C2776459999 @default.
• W4288064690 hasConceptScore W4288064690C2988773926 @default.
• W4288064690 hasConceptScore W4288064690C31487907 @default.
• W4288064690 hasConceptScore W4288064690C31972630 @default.
• W4288064690 hasConceptScore W4288064690C36464697 @default.
• W4288064690 hasConceptScore W4288064690C39890363 @default.
• W4288064690 hasConceptScore W4288064690C41008148 @default.
• W4288064690 hasConceptScore W4288064690C50644808 @default.
• W4288064690 hasConceptScore W4288064690C66629338 @default.
• W4288064690 hasConceptScore W4288064690C76155785 @default.
• W4288064690 hasConceptScore W4288064690C77660652 @default.
• W4288064690 hasFunder F4320306108 @default.
• W4288064690 hasIssue "12" @default.

• next