Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Helisa Dhamo"'
With the advent of deep learning, estimating depth from a single RGB image has recently received a lot of attention, being capable of empowering many different applications ranging from path planning for robotics to computational cinematography. Neve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf46121d5edd6c245ad350ef0f243da0
http://arxiv.org/abs/2112.01521
http://arxiv.org/abs/2112.01521
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Despite recent advancements in single-domain or single-object image generation, it is still challenging to generate complex scenes containing diverse, multiple objects and their interactions. Scene graphs, composed of nodes as objects and directed-ed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b84a6d97407953690cbfd7c88d534d6
https://doi.org/10.1109/iccv48922.2021.01605
https://doi.org/10.1109/iccv48922.2021.01605
Controllable scene synthesis consists of generating 3D information that satisfy underlying specifications. Thereby, these specifications should be abstract, i.e. allowing easy user interaction, whilst providing enough interface for detailed control.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e45a64c64dfe8e945874c17261c5a6d4
http://arxiv.org/abs/2108.08841
http://arxiv.org/abs/2108.08841
Publikováno v:
CVPR
Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic segmentation a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a5d46e1cb23f9f2a842d6a7e9d4a0185
Autor:
Azade Farshad, Christian Rupprecht, Federico Tombari, Helisa Dhamo, Nassir Navab, Gregory D. Hager, Iro Laina
Publikováno v:
CVPR
Image manipulation can be considered a special case of image generation where the image to be produced is a modification of an existing image. Image generation and manipulation have been, for the most part, tasks that operate on raw pixels. However,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6669defcf44aa4e1eac84a3ff66666b7
Publikováno v:
ICCV
We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation that arran
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21e92b1ab9467c64fe20aed70d1a05fb
https://doi.org/10.1109/iccv.2019.00547
https://doi.org/10.1109/iccv.2019.00547
While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of depth prediction in augmented and virtual reality applic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::739c88fc504908a467e55441d7df320f
http://arxiv.org/abs/1807.08776
http://arxiv.org/abs/1807.08776