Zobrazeno 1 - 10
of 502
pro vyhledávání: '"Sing Bing Kang"'
Publikováno v:
IEEE Access, Vol 7, Pp 23187-23196 (2019)
We describe a learning-based technique to automatically convert a 2-D panorama to its stereoscopic version. In particular, we train a generative adversarial network using perspective stereo pairs as inputs. Given a 2-D panorama, we partition it into
Externí odkaz:
https://doaj.org/article/0b46f81381a74f76910e171e23c3429e
Autor:
Tiancheng Zhi, Bowei Chen, Ivaylo Boyadzhiev, Sing Bing Kang, Martial Hebert, Srinivasa G. Narasimhan
We describe a novel approach to decompose a single panorama of an empty indoor environment into four appearance components: specular, direct sunlight, diffuse and diffuse ambient without direct sunlight. Our system is weakly supervised by automatical
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca350d8781bd95b004a3f5900d6dc2d0
http://arxiv.org/abs/2205.13150
http://arxiv.org/abs/2205.13150
Autor:
John Lambert, Yuguang Li, Ivaylo Boyadzhiev, Lambert Wixson, Manjunath Narayana, Will Hutchcroft, James Hays, Frank Dellaert, Sing Bing Kang
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198205
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6b57b14ba591a057ad9abaf9fbd80f5
https://doi.org/10.1007/978-3-031-19821-2_37
https://doi.org/10.1007/978-3-031-19821-2_37
Autor:
Zhixiang Min, Naji Khosravan, Zachary Bessinger, Manjunath Narayana, Sing Bing Kang, Enrique Dunn, Ivaylo Boyadzhiev
We present LASER, an image-based Monte Carlo Localization (MCL) framework for 2D floor maps. LASER introduces the concept of latent space rendering, where 2D pose hypotheses on the floor map are directly rendered into a geometrically-structured laten
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b04a8c3a3aa67a8635c53cdd707112ca
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198236
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8313b5ec76afc1c7ff9a2fb32c27487
https://doi.org/10.1007/978-3-031-19824-3_36
https://doi.org/10.1007/978-3-031-19824-3_36
Autor:
Haiyan Wang, Will Hutchcroft, Yuguang Li, Zhiqiang Wan, Ivaylo Boyadzhiev, Yingli Tian, Sing Bing Kang
In this paper, we propose a new deep learning-based method for estimating room layout given a pair of 360 panoramas. Our system, called Position-aware Stereo Merging Network or PSMNet, is an end-to-end joint layout-pose estimator. PSMNet consists of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04a0a9cf9a11fbcf187c2e26efe9f7c6
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f9620327986785bf8ddc98e2048619a
https://doi.org/10.1109/iccv48922.2021.00499
https://doi.org/10.1109/iccv48922.2021.00499
Publikováno v:
CVPR
We present Zillow Indoor Dataset (ZInD): A large indoor dataset with 71,474 panoramas from 1,524 real unfurnished homes. ZInD provides annotations of 3D room layouts, 2D and 3D floor plans, panorama location in the floor plan, and locations of window
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ff09021966ac7b3f6988ebdd3a0cf442
https://doi.org/10.1109/cvpr46437.2021.00217
https://doi.org/10.1109/cvpr46437.2021.00217
Autor:
Sing Bing Kang
Publikováno v:
Computer Vision ISBN: 9783030032432
Computer Vision
Computer Vision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::60988f76acc61a550a2f16cc3cbbb55e
https://doi.org/10.1007/978-3-030-03243-2_795-1
https://doi.org/10.1007/978-3-030-03243-2_795-1