MagicPony: Learning Articulated 3D Animals in the Wild

Autor: Wu, S, Li, R, Jakab, T, Rupprecht, C, Vedaldi, A

We consider the problem of predicting the 3D shape, articulation, viewpoint, texture, and lighting of an articulated animal like a horse given a single test image as input. We present a new method, dubbed MagicPony, that learns this predictor purely

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d9c325ca01ebc1dd4be6a5ac45f21a3
http://arxiv.org/abs/2211.12497

Learning human pose from unaligned data through image translation

Autor: Jakab, T, Vedaldi, A

We introduce a method for learning 2D landmark detectors for human pose from unlabelled video frames and unpaired human keypoints. We formulate this as an imageto-image translation task, similar to CycleGAN, between appearance (RGB) images and skelet

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______1064::d9b339de354babfadbb9a5374da4d26b
https://ora.ox.ac.uk/objects/uuid:8dec97ea-0d34-4d53-8b4e-8fb22f601473

Unsupervised Learning of Object Landmarks through Conditional Image Generation

Autor: Jakab, T, Gupta, A, Bilen, H, Vedaldi, A

Publikováno v: Jakab, T, Gupta, A, Bilen, H & Vedaldi, A 2018, Unsupervised Learning of Object Landmarks through Conditional Image Generation . in Proceedings of the 32nd Conference on Neural Information Processing Systems (NIPS 2018) . Palais des Congrès de Montréal, Montréal CANADA, pp. 1-12, Thirty-second Conference on Neural Information Processing Systems, Montreal, Canada, 3/12/18 . < https://papers.nips.cc/paper/7657-unsupervised-learning-of-object-landmarks-through-conditional-image-generation.pdf >

We propose a method for learning landmark detectors for visual objects (such as the eyes and the nose in a face) without any manual supervision. We cast this as the problem of generating images that combine the appearance of the object as seen in a f

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01869641cdc3e0765642f9a1beacb3cd
https://www.pure.ed.ac.uk/ws/files/76860367/Jakab18.pdf

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.