Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Ji, Renhe"'
Autor:
Yang, Shurong, Li, Huadong, Wu, Juhao, Jing, Minhao, Li, Linze, Ji, Renhe, Liang, Jiajun, Fan, Haoqiang, Wang, Jin
Diffusion models have demonstrated superior performance in the field of portrait animation. However, current approaches relied on either visual or audio modality to control character movements, failing to exploit the potential of mixed-modal control.
Externí odkaz:
http://arxiv.org/abs/2408.14975
Autor:
Yang, Shurong, Li, Huadong, Wu, Juhao, Jing, Minhao, Li, Linze, Ji, Renhe, Liang, Jiajun, Fan, Haoqiang
Despite raw driving videos contain richer information on facial expressions than intermediate representations such as landmarks in the field of portrait animation, they are seldom the subject of research. This is due to two challenges inherent in por
Externí odkaz:
http://arxiv.org/abs/2405.20851
Autor:
Li, Huadong, Dong, Shichao, Wang, Jin, Fu, Rong, Jing, Minhao, Liang, Jiajun, Fan, Haoqiang, Ji, Renhe
This paper focuses on the area of RGB(visible)-NIR(near-infrared) cross-modality image registration, which is crucial for many downstream vision tasks to fully leverage the complementary information present in visible and infrared images. In this fie
Externí odkaz:
http://arxiv.org/abs/2405.19914
It is widely believed that sparse supervision is worse than dense supervision in the field of depth completion, but the underlying reasons for this are rarely discussed. To this end, we revisit the task of radar-camera depth completion and present a
Externí odkaz:
http://arxiv.org/abs/2312.00844
RGB-NIR fusion is a promising method for low-light imaging. However, high-intensity noise in low-light images amplifies the effect of structure inconsistency between RGB-NIR images, which fails existing algorithms. To handle this, we propose a new RG
Externí odkaz:
http://arxiv.org/abs/2303.06834
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by the unexpected learned identity representation on images. Termed as t
Externí odkaz:
http://arxiv.org/abs/2210.14457
This paper aims to interpret how deepfake detection models learn artifact features of images when just supervised by binary labels. To this end, three hypotheses from the perspective of image matching are proposed as follows. 1. Deepfake detection mo
Externí odkaz:
http://arxiv.org/abs/2207.09679
Deep image completion usually fails to harmonically blend the restored image into existing content, especially in the boundary area. This paper handles with this problem from a new perspective of creating a smooth transition and proposes a concise De
Externí odkaz:
http://arxiv.org/abs/1904.08060
Publikováno v:
In Journal of Manufacturing Systems October 2021 61:351-364
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:1104-1112
RGB-NIR fusion is a promising method for low-light imaging. However, high-intensity noise in low-light images amplifies the effect of structure inconsistency between RGB-NIR images, which fails existing algorithms. To handle this, we propose a new RG
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06085f5c0a197140e4ff98e74990d6bc
https://doi.org/10.1609/aaai.v36i1.19995
https://doi.org/10.1609/aaai.v36i1.19995