Zobrazeno 1 - 10
of 111
pro vyhledávání: '"Matthias Zwicker"'
Publikováno v:
ACM Transactions on Graphics. 41:1-23
Repetitive vector patterns are common in a variety of applications but can be challenging and tedious to create. Existing automatic synthesis methods target relatively simple, unstructured patterns such as discrete elements and continuous Bézier cur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ce14462121da0d37572b69671589b97
https://doi.org/10.1145/3528223.3530062
https://doi.org/10.1145/3528223.3530062
Autor:
Quan Zheng, Gordon Wetzstein, Gurprit Singh, Matthias Zwicker, Hans-Peter Seidel, Vahid Babaei
Publikováno v:
ACM Transactions on Graphics. 39:1-12
Modern 3D printers are capable of printing large-size light-field displays at high-resolutions. However, optimizing such displays in full 3D volume for a given light-field imagery is still a challenging task. Existing light field displays optimize ov
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1cdeaf0ddeecf3fc984d48414e054196
https://doi.org/10.1145/3414685.3417879
https://doi.org/10.1145/3414685.3417879
Publikováno v:
IEEE Transactions on Image Processing. 29:8721-8734
3D shape reconstruction from multiple hand-drawn sketches is an intriguing way to 3D shape modeling. Currently, state-of-the-art methods employ neural networks to learn a mapping from multiple sketches from arbitrary view angles to a 3D voxel grid. B
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9bfe077d9d7d1d1e0464158d577995ed
https://doi.org/10.1109/tip.2020.3018865
https://doi.org/10.1109/tip.2020.3018865
Autor:
Shuhong Chen, Matthias Zwicker
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197895
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::580213b21c092b4e5422f3d7823f3877
https://doi.org/10.1007/978-3-031-19790-1_17
https://doi.org/10.1007/978-3-031-19790-1_17
Publikováno v:
ICCV 2021
We present EgoRenderer, a system for rendering full-body neural avatars of a person captured by a wearable, egocentric fisheye camera that is mounted on a cap or a VR headset. Our system renders photorealistic novel views of the actor and her motion
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::867f00b9fc27b653b41c784fc5eae712
https://doi.org/10.1109/iccv48922.2021.01426
https://doi.org/10.1109/iccv48922.2021.01426
Publikováno v:
AAAI
Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to capture fine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce25b299e5187de0092026a713a0707f
https://doi.org/10.1609/aaai.v33i01.33018778
https://doi.org/10.1609/aaai.v33i01.33018778
Autor:
Matthias Zwicker, Quan Zheng
Publikováno v:
Computer Graphics Forum. 38:169-179
Importance sampling is one of the most widely used variance reduction strategies in Monte Carlo rendering. In this paper, we propose a novel importance sampling technique that uses a neural network to learn how to sample from a desired density repres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1ddc0459cb6699993ac75f0d7368cbc2
https://doi.org/10.1111/cgf.13628
https://doi.org/10.1111/cgf.13628
Autor:
Victor Petitjean, Toshiya Hachisuka, Adrien Gruson, Matthias Zwicker, Derek Nowrouzezahrai, Binh-Son Hua, Elmar Eisemann
Publikováno v:
Computer Graphics Forum. 38:455-472
Monte Carlo methods for physically-based light transport simulation are broadly adopted in the feature film production, animation and visual effects industries. These methods, however, often result in noisy images and have slow convergence. As such,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6c8d50401c6d15d15195ed66bfc7537
https://doi.org/10.1111/cgf.13652
https://doi.org/10.1111/cgf.13652
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics
Small object arrangement is very important for creating detailed and realistic 3D indoor scenes. In this article, we present an interactive framework based on active learning to help users create customized arrangements for small objects according to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9cd88eb23e784cfe1b8a142caacda095
https://orca.cardiff.ac.uk/id/eprint/126162/1/SmallObjectArrangementTVCG2019.pdf
https://orca.cardiff.ac.uk/id/eprint/126162/1/SmallObjectArrangementTVCG2019.pdf
Publikováno v:
ACM Multimedia
Unsupervised learning of global features for 3D shape analysis is an important research challenge because it avoids manual effort for supervised information collection. In this paper, we propose a view-based deep learning model called Hierarchical Vi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f1ede904d60d1cee0ee2468d83bc6d81