Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Lin, Hubert"'
The process of capturing a well-composed photo is difficult and it takes years of experience to master. We propose a novel pipeline for an autonomous agent to automatically capture an aesthetic photograph by navigating within a local region in a scen
Externí odkaz:
http://arxiv.org/abs/2109.09923
Autor:
van Zuijlen, Mitchell J. P., Lin, Hubert, Bala, Kavita, Pont, Sylvia C., Wijntjes, Maarten W. A.
A painter is free to modify how components of a natural scene are depicted, which can lead to a perceptually convincing image of the distal world. This signals a major difference between photos and paintings: paintings are explicitly created for huma
Externí odkaz:
http://arxiv.org/abs/2012.02996
A common strategy for improving model robustness is through data augmentations. Data augmentations encourage models to learn desired invariances, such as invariance to horizontal flipping or small changes in color. Recent work has shown that arbitrar
Externí odkaz:
http://arxiv.org/abs/2011.14477
Deep learning has paved the way for strong recognition systems which are often both trained on and applied to natural images. In this paper, we examine the give-and-take relationship between such visual recognition systems and the rich information av
Externí odkaz:
http://arxiv.org/abs/2011.12276
Planning in unstructured environments is challenging -- it relies on sensing, perception, scene reconstruction, and reasoning about various uncertainties. We propose DeepSemanticHPPC, a novel uncertainty-aware hypothesis-based planner for unstructure
Externí odkaz:
http://arxiv.org/abs/2003.03464
Image datasets with high-quality pixel-level annotations are valuable for semantic segmentation: labelling every pixel in an image ensures that rare classes and small objects are annotated. However, full-image annotations are expensive, with experts
Externí odkaz:
http://arxiv.org/abs/2002.06626
Autor:
Lin, Hubert, Averkiou, Melinos, Kalogerakis, Evangelos, Kovacs, Balazs, Ranade, Siddhant, Kim, Vladimir G., Chaudhuri, Siddhartha, Bala, Kavita
Material understanding is critical for design, geometric modeling, and analysis of functional objects. We enable material-aware 3D shape analysis by employing a projective convolutional neural network architecture to learn material- aware descriptors
Externí odkaz:
http://arxiv.org/abs/1810.08729
Autor:
Van Zuijlen, Mitchell J. P.1 (AUTHOR) m.j.p.vanzuijlen@tudelft.nl, Lin, Hubert2 (AUTHOR), Bala, Kavita2 (AUTHOR), Pont, Sylvia C.1 (AUTHOR), Wijntjes, Maarten W. A.1 (AUTHOR)
Publikováno v:
PLoS ONE. 8/26/2021, Vol. 16 Issue 8, p1-30. 30p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.