Zobrazeno 1 - 10
of 162
pro vyhledávání: '"Ukita, Norimichi"'
While burst LR images are useful for improving the SR image quality compared with a single LR image, prior SR networks accepting the burst LR images are trained in a deterministic manner, which is known to produce a blurry SR image. In addition, it i
Externí odkaz:
http://arxiv.org/abs/2403.19428
Autor:
Shimosato, Kodai, Ukita, Norimichi
This paper proposes a mask optimization method for improving the quality of object removal using image inpainting. While many inpainting methods are trained with a set of random masks, a target for inpainting may be an object, such as a person, in ma
Externí odkaz:
http://arxiv.org/abs/2403.15849
Autor:
Mori, Hiroshi, Ukita, Norimichi
A Recurrent Neural Network (RNN) for Video Super Resolution (VSR) is generally trained with randomly clipped and cropped short videos extracted from original training videos due to various challenges in learning RNNs. However, since this RNN is optim
Externí odkaz:
http://arxiv.org/abs/2403.15832
This paper proposes a depth estimation method using radar-image fusion by addressing the uncertain vertical directions of sparse radar measurements. In prior radar-image fusion work, image features are merged with the uncertain sparse depths measured
Externí odkaz:
http://arxiv.org/abs/2403.15787
In this paper, we analyze and discuss ShadowFormer in preparation for the NTIRE2023 Shadow Removal Challenge [1], implementing five key improvements: image alignment, the introduction of a perceptual quality loss function, the semi-automatic annotati
Externí odkaz:
http://arxiv.org/abs/2403.08995
This paper proposes Group Activity Feature (GAF) learning in which features of multi-person activity are learned as a compact latent vector. Unlike prior work in which the manual annotation of group activities is required for supervised learning, our
Externí odkaz:
http://arxiv.org/abs/2403.02753
Autor:
Taketsugu, Hiromu, Ukita, Norimichi
Human Pose (HP) estimation is actively researched because of its wide range of applications. However, even estimators pre-trained on large datasets may not perform satisfactorily due to a domain gap between the training and test data. To address this
Externí odkaz:
http://arxiv.org/abs/2311.05041
For physical human-robot interactions (pHRI), a robot needs to estimate the accurate body pose of a target person. However, in these pHRI scenarios, the robot cannot fully observe the target person's body with equipped cameras because the target pers
Externí odkaz:
http://arxiv.org/abs/2310.08116
Autor:
Maeda, Takahiro, Ukita, Norimichi
Safety-critical applications such as autonomous vehicles and social robots require fast computation and accurate probability density estimation on trajectory prediction. To address both requirements, this paper presents a new normalizing flow-based t
Externí odkaz:
http://arxiv.org/abs/2308.08824
This paper proposes joint attention estimation in a single image. Different from related work in which only the gaze-related attributes of people are independently employed, (I) their locations and actions are also employed as contextual cues for wei
Externí odkaz:
http://arxiv.org/abs/2308.05382