Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312541905> ?p ?o ?g. }
- W4312541905 endingPage "327" @default.
- W4312541905 startingPage "310" @default.
- W4312541905 abstract "Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed by two seemingly opposed approaches: improving the realism of simulation or foregoing realism entirely via domain randomization. In this paper, we show that the recent progress in neural rendering enables a new unified approach we call Photo-realistic Neural Domain Randomization (PNDR). We propose to learn a composition of neural networks that acts as a physics-based ray tracer generating high-quality renderings from scene geometry alone. Our approach is modular, composed of different neural networks for materials, lighting, and rendering, thus enabling randomization of different key image generation components in a differentiable pipeline. Once trained, our method can be combined with other methods and used to generate photo-realistic image augmentations online and significantly more efficiently than via traditional ray-tracing. We demonstrate the usefulness of PNDR through two downstream tasks: 6D object detection and monocular depth estimation. Our experiments show that training with PNDR enables generalization to novel scenes and significantly outperforms the state of the art in terms of real-world transfer." @default.
- W4312541905 created "2023-01-05" @default.
- W4312541905 creator A5000146074 @default.
- W4312541905 creator A5005399215 @default.
- W4312541905 creator A5037522398 @default.
- W4312541905 creator A5063755961 @default.
- W4312541905 creator A5075018873 @default.
- W4312541905 date "2022-01-01" @default.
- W4312541905 modified "2023-10-18" @default.
- W4312541905 title "Photo-realistic Neural Domain Randomization" @default.
- W4312541905 cites W1731081199 @default.
- W4312541905 cites W1979606301 @default.
- W4312541905 cites W2103607478 @default.
- W4312541905 cites W2133665775 @default.
- W4312541905 cites W2311236754 @default.
- W4312541905 cites W2584009249 @default.
- W4312541905 cites W2605102758 @default.
- W4312541905 cites W2605183293 @default.
- W4312541905 cites W2942074357 @default.
- W4312541905 cites W2962785568 @default.
- W4312541905 cites W2962793481 @default.
- W4312541905 cites W2963038612 @default.
- W4312541905 cites W2963073614 @default.
- W4312541905 cites W2963201472 @default.
- W4312541905 cites W2963756608 @default.
- W4312541905 cites W2963800363 @default.
- W4312541905 cites W2963835812 @default.
- W4312541905 cites W2963890451 @default.
- W4312541905 cites W2963892972 @default.
- W4312541905 cites W2964057616 @default.
- W4312541905 cites W2964249569 @default.
- W4312541905 cites W2968638474 @default.
- W4312541905 cites W2970399728 @default.
- W4312541905 cites W2981378444 @default.
- W4312541905 cites W2985406498 @default.
- W4312541905 cites W2985775862 @default.
- W4312541905 cites W2985936292 @default.
- W4312541905 cites W2987651531 @default.
- W4312541905 cites W2989915422 @default.
- W4312541905 cites W2994152969 @default.
- W4312541905 cites W3004023976 @default.
- W4312541905 cites W3011972190 @default.
- W4312541905 cites W3034268164 @default.
- W4312541905 cites W3034604951 @default.
- W4312541905 cites W3092774272 @default.
- W4312541905 cites W3100052745 @default.
- W4312541905 cites W3108316907 @default.
- W4312541905 cites W3108325989 @default.
- W4312541905 cites W3109585842 @default.
- W4312541905 cites W3110015970 @default.
- W4312541905 cites W3119635706 @default.
- W4312541905 cites W3159890710 @default.
- W4312541905 cites W3175502768 @default.
- W4312541905 cites W3176179930 @default.
- W4312541905 cites W3183988645 @default.
- W4312541905 cites W3195620846 @default.
- W4312541905 cites W3203651076 @default.
- W4312541905 cites W3204455502 @default.
- W4312541905 cites W3206481472 @default.
- W4312541905 cites W4214608804 @default.
- W4312541905 cites W4230194115 @default.
- W4312541905 cites W4286615883 @default.
- W4312541905 cites W62794737 @default.
- W4312541905 doi "https://doi.org/10.1007/978-3-031-19806-9_18" @default.
- W4312541905 hasPublicationYear "2022" @default.
- W4312541905 type Work @default.
- W4312541905 citedByCount "1" @default.
- W4312541905 countsByYear W43125419052023 @default.
- W4312541905 crossrefType "book-chapter" @default.
- W4312541905 hasAuthorship W4312541905A5000146074 @default.
- W4312541905 hasAuthorship W4312541905A5005399215 @default.
- W4312541905 hasAuthorship W4312541905A5037522398 @default.
- W4312541905 hasAuthorship W4312541905A5063755961 @default.
- W4312541905 hasAuthorship W4312541905A5075018873 @default.
- W4312541905 hasBestOaLocation W43125419052 @default.
- W4312541905 hasConcept C101468663 @default.
- W4312541905 hasConcept C134306372 @default.
- W4312541905 hasConcept C154945302 @default.
- W4312541905 hasConcept C199360897 @default.
- W4312541905 hasConcept C202615002 @default.
- W4312541905 hasConcept C205711294 @default.
- W4312541905 hasConcept C31972630 @default.
- W4312541905 hasConcept C33923547 @default.
- W4312541905 hasConcept C36464697 @default.
- W4312541905 hasConcept C36503486 @default.
- W4312541905 hasConcept C41008148 @default.
- W4312541905 hasConcept C48044578 @default.
- W4312541905 hasConcept C50644808 @default.
- W4312541905 hasConcept C65909025 @default.
- W4312541905 hasConcept C77088390 @default.
- W4312541905 hasConceptScore W4312541905C101468663 @default.
- W4312541905 hasConceptScore W4312541905C134306372 @default.
- W4312541905 hasConceptScore W4312541905C154945302 @default.
- W4312541905 hasConceptScore W4312541905C199360897 @default.
- W4312541905 hasConceptScore W4312541905C202615002 @default.
- W4312541905 hasConceptScore W4312541905C205711294 @default.
- W4312541905 hasConceptScore W4312541905C31972630 @default.
- W4312541905 hasConceptScore W4312541905C33923547 @default.