Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Christoph Bregler"'
Publikováno v:
SIGGRAPH Asia 2022 Technical Communications.
Alpha matting is widely used in video conferencing as well as in movies, television, and social media sites. Deep learning approaches to the matte extraction problem are well suited to video conferencing due to the consistent subject matter (front-fa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39085eb0260546841780a89ab6ac554f
https://doi.org/10.1145/3550340.3564230
https://doi.org/10.1145/3550340.3564230
Autor:
Christoph Bregler
Publikováno v:
Computer Vision ISBN: 9783030032432
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c142be2aa687195cec2be276f26ce53
https://doi.org/10.1007/978-3-030-63416-2_587
https://doi.org/10.1007/978-3-030-63416-2_587
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585259
ECCV (29)
ECCV (29)
With a proliferation of generic domain-adaptation approaches, we report a simple yet effective technique for learning difficult per-pixel 2.5D and 3D regression representations of articulated people. We obtained strong sim-to-real domain generalizati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da97278563234a9497f4c878afec4b6b
https://doi.org/10.1007/978-3-030-58526-6_14
https://doi.org/10.1007/978-3-030-58526-6_14
Autor:
Erika Chuang, Christoph Bregler
Publikováno v:
ACM Transactions on Graphics. 24:331-347
Motion capture-based facial animation has recently gained popularity in many applications, such as movies, video games, and human-computer interface designs. With the use of sophisticated facial motions from a human performer, animated characters are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3cec4dd7c72a09086594fb95c82e00de
https://doi.org/10.1145/1061347.1061355
https://doi.org/10.1145/1061347.1061355
Publikováno v:
International Journal of Computer Vision. 56:179-194
This paper demonstrates a new visual motion estimation technique that is able to recover high degree-of-freedom articulated human body configurations in complex video sequences. We introduce the use and integration of a mathematical technique, the pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ff57bc0a505e5b8b01daf58ec6c45f92
https://doi.org/10.1023/b:visi.0000011203.00237.9b
https://doi.org/10.1023/b:visi.0000011203.00237.9b
Publikováno v:
Computer Vision--ACCV 2014 ISBN: 9783319168074
ACCV (2)
ACCV (2)
In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features. We propose a new human body pose dataset, FLIC-motion
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50857de3123e23413dead1138568af86
https://doi.org/10.1007/978-3-319-16808-1_21
https://doi.org/10.1007/978-3-319-16808-1_21
Publikováno v:
CVPR
Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling and sub-sampling layers which reduce computational requirements, introd
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1345ed6fe8d723b87812efcf5417717
Publikováno v:
COSN
While Online Social Networks (OSNs) enable users to share photos easily, they also expose users to several privacy threats from both the OSNs and external entities. The current privacy controls on OSNs are far from adequate, resulting in inappropriat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5613b58fb1f7b4441e9d9f04f6f790d5
https://doi.org/10.1145/2512938.2512939
https://doi.org/10.1145/2512938.2512939
Publikováno v:
CVPR Workshops
This paper demonstrates how 3D skeletal reconstruction can be performed by using a pose-sensitive embedding technique applied to multi-view video recordings. We apply our approach to challenging low-resolution video sequences. Usually skeletal recons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7afee5bc089ff453411a56972796dfa5
https://doi.org/10.1109/cvprw.2012.6239238
https://doi.org/10.1109/cvprw.2012.6239238
Publikováno v:
CVPR
Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approaches rely on binary similarity, typically defined by class membership wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a8ff956a4a1d62b18f876f3e35d76a0
https://doi.org/10.1109/cvpr.2011.5995538
https://doi.org/10.1109/cvpr.2011.5995538