Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Lim, Isaak"'
Autor:
Elsner, Tim, Usinger, Paula, Nehring-Wirxel, Julius, Kobsik, Gregor, Czech, Victor, He, Yanjiang, Lim, Isaak, Kobbelt, Leif
In language processing, transformers benefit greatly from text being condensed. This is achieved through a larger vocabulary that captures word fragments instead of plain characters. This is often done with Byte Pair Encoding. In the context of image
Externí odkaz:
http://arxiv.org/abs/2411.10281
Autor:
Elsner, Tim, Usinger, Paula, Czech, Victor, Kobsik, Gregor, He, Yanjiang, Lim, Isaak, Kobbelt, Leif
In quantised autoencoders, images are usually split into local patches, each encoded by one token. This representation is redundant in the sense that the same number of tokens is spend per region, regardless of the visual information content in that
Externí odkaz:
http://arxiv.org/abs/2407.11913
Symmetry detection, especially partial and extrinsic symmetry, is essential for various downstream tasks, like 3D geometry completion, segmentation, compression and structure-aware shape encoding or generation. In order to detect partial extrinsic sy
Externí odkaz:
http://arxiv.org/abs/2312.08230
Neural Radiance Fields (NeRFs) learn to represent a 3D scene from just a set of registered images. Increasing sizes of a scene demands more complex functions, typically represented by neural networks, to capture all details. Training and inference th
Externí odkaz:
http://arxiv.org/abs/2303.16001
Although massive pre-trained vision-language models like CLIP show impressive generalization capabilities for many tasks, still it often remains necessary to fine-tune them for improved performance on specific datasets. When doing so, it is desirable
Externí odkaz:
http://arxiv.org/abs/2212.06556
Previous approaches to generate shapes in a 3D setting train a GAN on the latent space of an autoencoder (AE). Even though this produces convincing results, it has two major shortcomings. As the GAN is limited to reproduce the dataset the AE was trai
Externí odkaz:
http://arxiv.org/abs/2107.10607
Publikováno v:
Computer Graphics Forum 38 (5), 2019
Automatic synthesis of high quality 3D shapes is an ongoing and challenging area of research. While several data-driven methods have been proposed that make use of neural networks to generate 3D shapes, none of them reach the level of quality that de
Externí odkaz:
http://arxiv.org/abs/1906.11478
The question of representation of 3D geometry is of vital importance when it comes to leveraging the recent advances in the field of machine learning for geometry processing tasks. For common unstructured surface meshes state-of-the-art methods rely
Externí odkaz:
http://arxiv.org/abs/1809.06664
Autor:
Dielen, Alexander1 (AUTHOR), Lim, Isaak1 (AUTHOR), Lyon, Max1 (AUTHOR), Kobbelt, Leif1 (AUTHOR)
Publikováno v:
Computer Graphics Forum. Aug2021, Vol. 40 Issue 5, p181-191. 11p. 2 Black and White Photographs, 4 Diagrams, 1 Chart, 5 Graphs.
Publikováno v:
Computer Graphics Forum. May2019, Vol. 38 Issue 2, p27-36. 10p. 10 Diagrams, 2 Charts.