Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Buhmann, Jakob"'
Modern pose estimation models are trained on large, manually-labelled datasets which are costly and may not cover the full extent of human poses and appearances in the real world. With advances in neural rendering, analysis-by-synthesis and the abili
Externí odkaz:
http://arxiv.org/abs/2411.08603
Advances in latent diffusion models (LDMs) have revolutionized high-resolution image generation, but the design space of the autoencoder that is central to these systems remains underexplored. In this paper, we introduce LiteVAE, a family of autoenco
Externí odkaz:
http://arxiv.org/abs/2405.14477
Publikováno v:
The Twelfth International Conference on Learning Representations (ICLR 2024)
While conditional diffusion models are known to have good coverage of the data distribution, they still face limitations in output diversity, particularly when sampled with a high classifier-free guidance scale for optimal image quality or when train
Externí odkaz:
http://arxiv.org/abs/2310.17347
Movie productions use high resolution 3d characters with complex proprietary rigs to create the highest quality images possible for large displays. Unfortunately, these 3d assets are typically not compatible with real-time graphics engines used for g
Externí odkaz:
http://arxiv.org/abs/2003.09820
Developing intelligent virtual characters has attracted a lot of attention in the recent years. The process of creating such characters often involves a team of creative authors who describe different aspects of the characters in natural language, an
Externí odkaz:
http://arxiv.org/abs/1904.03266
Publikováno v:
ACM Transactions on Graphics; Dec2024, Vol. 43 Issue 6, p1-11, 11p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.