Zobrazeno 1 - 10
of 24
pro vyhledávání: '"XINGANG PAN"'
Autor:
TEOTIA, KARTIK, B. R., MALLIKARJUN, XINGANG PAN, HYEONGWOO KIM, GARRIDO, PABLO, ELGHARIB, MOHAMED, THEOBALT, CHRISTIAN
Publikováno v:
ACM Transactions on Graphics; Jun2024, Vol. 43 Issue 3, p1-24, 24p
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:7474-7489
Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich image semanti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::46353ce77fd500e50302c38510e35d4c
https://doi.org/10.1109/tpami.2021.3115428
https://doi.org/10.1109/tpami.2021.3115428
Facial editing is an important task in vision and graphics with numerous applications. However, existing works are incapable to deliver a continuous and fine-grained editing mode (e.g., editing a slightly smiling face to a big laughing one) with natu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51d057dcdd31858c26a33bf3e81eef27
Autor:
Yuanbo Xiangli, Linning Xu, Xingang Pan, Nanxuan Zhao, Anyi Rao, Christian Theobalt, Bo Dai, Dahua Lin
Publikováno v:
Computer Vision--ECCV 2022
Lecture Notes in Computer Science
Lecture Notes in Computer Science ISBN: 9783031198236
Lecture Notes in Computer Science
Lecture Notes in Computer Science ISBN: 9783031198236
Neural radiance fields (NeRF) has achieved outstanding performance in modeling 3D objects and controlled scenes, usually under a single scale. In this work, we focus on multi-scale cases where large changes in imagery are observed at drastically diff
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83e3f4f612c3a37b72160864c69cfc34
Publikováno v:
CVPR
Natural scene understanding is a challenging task, particularly when encountering images of multiple objects that are partially occluded. This obstacle is given rise by varying object ordering and positioning. Existing scene understanding paradigms a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a642931f65779d7f89219bcfc7031a5
http://arxiv.org/abs/2004.02788
http://arxiv.org/abs/2004.02788
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585358
ECCV (2)
ECCV (2)
Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich image semanti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61b602059376b8d9e03e8228e042017d
https://doi.org/10.1007/978-3-030-58536-5_16
https://doi.org/10.1007/978-3-030-58536-5_16
Publikováno v:
CVPR
Intelligent agent naturally learns from motion. Various self-supervised algorithms have leveraged motion cues to learn effective visual representations. The hurdle here is that motion is both ambiguous and complex, rendering previous works either suf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70deabb79d265594a0d1c17130ecc555
http://arxiv.org/abs/1903.11412
http://arxiv.org/abs/1903.11412
Publikováno v:
CVPR
A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e.g., sunny weather) for achieving high performance on the test data in a target domain (e.g., rainy weather). Whether the target contains a sin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::900082f90477926f106ec103604357d6
Publikováno v:
ICCV
Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design normalization techniques for spe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08a5cac5430730282e7796810626c40b
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012243
ECCV (4)
ECCV (4)
Convolutional neural networks (CNNs) have achieved great successes in many computer vision problems. Unlike existing works that designed CNN architectures to improve performance on a single task of a single domain and not generalizable, we present IB
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8248168445a60fd74236fe5681a4405c
https://doi.org/10.1007/978-3-030-01225-0_29
https://doi.org/10.1007/978-3-030-01225-0_29