Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Yuki Endo"'
Autor:
Yuki Endo, Yoshihiro Kanamori
Publikováno v:
ACM Transactions on Graphics. 37:1-11
Relighting of human images has various applications in image synthesis. For relighting, we must infer albedo, shape, and illumination from a human portrait. Previous techniques rely on human faces for this inference, based on spherical harmonics (SH)
Autor:
Yuki Endo, Yoshihiro Kanamori
Semantic image synthesis is a process for generating photorealistic images from a single semantic mask. To enrich the diversity of multimodal image synthesis, previous methods have controlled the global appearance of an output image by learning a sin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::abad69a89795ac2c1e8d4e1e887491de
Publikováno v:
Computational Visual Media, Vol 4, Iss 1, Pp 43-54 (2018)
Parsing of human images is a fundamental task for determining semantic parts such as the face, arms, and legs, as well as a hat or a dress. Recent deep-learning-based methods have achieved significant improvements, but collecting training datasets wi
Publikováno v:
ACM Transactions on Graphics. 36:1-10
Inferring a high dynamic range (HDR) image from a single low dynamic range (LDR) input is an ill-posed problem where we must compensate lost data caused by under-/over-exposure and color quantization. To tackle this, we propose the first deep-learnin
Publikováno v:
Computer Graphics Forum. 36:41-50
Publikováno v:
International Journal of Data Science and Analytics. 2:107-117
This paper addresses the problem of feature extraction for estimating users’ transportation modes from their movement trajectories. Previous studies have adopted supervised learning approaches and used engineers’ skills to find effective features
Publikováno v:
Computer Graphics Forum. 35:189-201
Edit propagation is a technique that can propagate various image edits (e.g., colorization and recoloring) performed via user strokes to the entire image based on similarity of image features. In most previous work, users must manually determine the
Publikováno v:
Computer Graphics Forum. 35:501-509
This paper presents an efficient approach for generating weathering effects with detailed appearance variations in a single image. Previous approaches merely change chroma or reflectance of weathered objects, which is not sufficient for materials wit
Publikováno v:
2017 International Conference on Biometrics and Kansei Engineering (ICBAKE).
It is extremely difficult for visually impaired people to walk in strange places, because it is extremely challenging for them to know where they are, the direction in which to move, and the destination. Pedestrian navigation systems such as Google M
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783319574530
PAKDD (1)
PAKDD (1)
Predicting a user’s destinations from his or her partial movement trajectories is still a challenging problem. To this end, we employ recurrent neural networks (RNNs), which can consider long-term dependencies and avoid a data sparsity problem. Thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7c7090c342a8adf431321b0aa6c446c5
https://doi.org/10.1007/978-3-319-57454-7_13
https://doi.org/10.1007/978-3-319-57454-7_13