Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Tai-Jiang Mu"'
Publikováno v:
Graphical Models, Vol 136, Iss , Pp 101231- (2024)
Sketch-based content generation offers flexible controllability, making it a promising narrative avenue in film production. Directors often visualize their imagination by crafting storyboards using sketches and textual descriptions for each shot. How
Externí odkaz:
https://doaj.org/article/b3d973f3f0504581b48d19106364dab2
Publikováno v:
Computational Visual Media, Vol 9, Iss 3, Pp 407-442 (2023)
Abstract Deep learning has been successfully used for tasks in the 2D image domain. Research on 3D computer vision and deep geometry learning has also attracted attention. Considerable achievements have been made regarding feature extraction and disc
Externí odkaz:
https://doaj.org/article/564f6e0692a14273ac6cc2505f9ec7a1
Publikováno v:
Computational Visual Media, Vol 9, Iss 4, Pp 687-697 (2023)
Abstract Sparse view 3D reconstruction has attracted increasing attention with the development of neural implicit 3D representation. Existing methods usually only make use of 2D views, requiring a dense set of input views for accurate 3D reconstructi
Externí odkaz:
https://doaj.org/article/9c0f7e901ba2431f9287a0c3d96c9031
Publikováno v:
Computational Visual Media, Vol 7, Iss 3, Pp 283-288 (2021)
Externí odkaz:
https://doaj.org/article/afbaa95097f945ff847cf3fbdf8a4b51
Publikováno v:
Computational Visual Media, Vol 6, Iss 4, Pp 477-487 (2020)
Abstract In this paper, we introduce an image dataset for fine-grained classification of dog breeds: the Tsinghua Dogs Dataset. It is currently the largest dataset for fine-grained classification of dogs, including 130 dog breeds and 70,428 real-worl
Externí odkaz:
https://doaj.org/article/44d51d16fa2f4df78f757ea821f553af
Publikováno v:
Computational Visual Media, Vol 7, Iss 2, Pp 229-239 (2020)
Abstract Human–object interaction (HOI) detection is crucial for human-centric image understanding which aims to infer ⟨human, action, object⟩ triplets within an image. Recent studies often exploit visual features and the spatial configuration
Externí odkaz:
https://doaj.org/article/f325410c49b34750b95815766948c217
Publikováno v:
Computational Visual Media, Vol 6, Iss 2, Pp 191-204 (2020)
Abstract In this paper, we consider salient instance segmentation. As well as producing bounding boxes, our network also outputs high-quality instance-level segments as initial selections to indicate the regions of interest. Taking into account the c
Externí odkaz:
https://doaj.org/article/b1011967c56d43f18e65eed0940c3a70
Publikováno v:
Computational Visual Media, Vol 5, Iss 4, Pp 417-428 (2020)
Abstract In this paper, we propose a simple but effective framework for lane boundary detection, called SpinNet. Considering that cars or pedestrians often occlude lane boundaries and that the local features of lane boundaries are not distinctive, th
Externí odkaz:
https://doaj.org/article/4787f70ecadf4d1c9498172b8a8632cc
Publikováno v:
Computational Visual Media, Vol 3, Iss 4, Pp 337-347 (2017)
Abstract Current image-editing tools do not match up to the demands of personalized image manipulation, one application of which is changing clothes in usercaptured images. Previous work can change single color clothes using parametric human warping
Externí odkaz:
https://doaj.org/article/b9ca336d10e548a1a924e3ac37bbdc59
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. :1-14