Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Angel X. Chang"'
Human-object interactions with articulated objects are common in everyday life. Despite much progress in single-view 3D reconstruction, it is still challenging to infer an articulated 3D object model from an RGB video showing a person manipulating th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41fd59b338e349629bbcdbc07c4425cd
http://arxiv.org/abs/2209.05612
http://arxiv.org/abs/2209.05612
Publikováno v:
2022 19th Conference on Robots and Vision (CRV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8c9ce07c123485f1fcc365eff5ab388
https://doi.org/10.1109/crv55824.2022.00038
https://doi.org/10.1109/crv55824.2022.00038
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198236
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cebbb9d09a1826a97dddb013a4d59643
https://doi.org/10.1007/978-3-031-19824-3_29
https://doi.org/10.1007/978-3-031-19824-3_29
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198410
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf91c12c981f57559f096f1b332269c9
https://doi.org/10.1007/978-3-031-19842-7_24
https://doi.org/10.1007/978-3-031-19842-7_24
Publikováno v:
ACM Transactions on Graphics. 38:1-15
We present a new framework for interior scene synthesis that combines a high-level relation graph representation with spatial prior neural networks. We observe that prior work on scene synthesis is divided into two camps: object-oriented approaches (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0453a62d47d62430c7cc534460b3b092
https://doi.org/10.1145/3306346.3322941
https://doi.org/10.1145/3306346.3322941
Publikováno v:
CVPR
Despite recent progress in depth sensing and 3D reconstruction, mirror surfaces are a significant source of errors. To address this problem, we create the Mirror3D dataset: a 3D mirror plane dataset based on three RGBD datasets (Matterport3D, NYUv2 a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::340c301647d2dba0fdd5564849d6b180
http://arxiv.org/abs/2106.06629
http://arxiv.org/abs/2106.06629
Publikováno v:
CVPR
We address the task of converting a floorplan and a set of associated photos of a residence into a textured 3D mesh model, a task which we call Plan2Scene. Our system 1) lifts a floorplan image to a 3D mesh model; 2) synthesizes surface textures base
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2771d001d38721fb033d57a45a26140b
http://arxiv.org/abs/2106.05375
http://arxiv.org/abs/2106.05375
Publikováno v:
CVPR
We introduce the task of dense captioning in 3D scans from commodity RGB-D sensors. As input, we assume a point cloud of a 3D scene; the expected output is the bounding boxes along with the descriptions for the underlying objects. To address the 3D o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::304a880372b669aa5d3bd6f5e8d664fb
https://doi.org/10.1109/cvpr46437.2021.00321
https://doi.org/10.1109/cvpr46437.2021.00321
Autor:
Daniel Ritchie, Xianghao Xu, Sonia Raychaudhuri, Mae Heitmann, Hanxiao Jiang, Angel X. Chang, Manolis Savva, Vladimir G. Kim, David Charatan, Siddhartha Chaudhuri
Publikováno v:
3DV
3D models of real-world objects are essential for many applications, including the creation of virtual environments for AI training. To mimic real-world objects in these applications, objects must be annotated with their kinematic mobilities. Annotat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::82e65665042eb02d83d9a88bb0cb964e
https://doi.org/10.1109/3dv50981.2020.00071
https://doi.org/10.1109/3dv50981.2020.00071
Publikováno v:
UIST
Natural language interaction has evolved as a useful modality to help users explore and interact with their data during visual analysis. Little work has been done to explore how autocompletion can help with data discovery while helping users formulat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::659755e04eed9a5d3fdb4d3df28df591
https://doi.org/10.1145/3379337.3415813
https://doi.org/10.1145/3379337.3415813