Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Rogez, Gregory"'
Aligning multiple modalities in a latent space, such as images and texts, has shown to produce powerful semantic visual representations, fueling tasks like image captioning, text-to-image generation, or image grounding. In the context of human-centri
Externí odkaz:
http://arxiv.org/abs/2409.06535
In this paper, we address the challenging problem of long-term 3D human motion generation. Specifically, we aim to generate a long sequence of smoothly connected actions from a stream of multiple sentences (i.e., paragraph). Previous long-term motion
Externí odkaz:
http://arxiv.org/abs/2406.00636
Autor:
Ugrinovic, Nicolas, Lucas, Thomas, Baradel, Fabien, Weinzaepfel, Philippe, Rogez, Gregory, Moreno-Noguer, Francesc
We present a novel method to generate human motion to populate 3D indoor scenes. It can be controlled with various combinations of conditioning signals such as a path in a scene, target poses, past motions, and scenes represented as 3D point clouds.
Externí odkaz:
http://arxiv.org/abs/2404.12942
When deploying a semantic segmentation model into the real world, it will inevitably encounter semantic classes that were not seen during training. To ensure a safe deployment of such systems, it is crucial to accurately evaluate and improve their an
Externí odkaz:
http://arxiv.org/abs/2402.16392
Autor:
Baradel, Fabien, Armando, Matthieu, Galaaoui, Salma, Brégier, Romain, Weinzaepfel, Philippe, Rogez, Grégory, Lucas, Thomas
We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image. Predictions encompass the whole body, i.e., including hands and facial expressions, using the SMPL-X parametric model and 3D location in
Externí odkaz:
http://arxiv.org/abs/2402.14654
Autor:
Armando, Matthieu, Galaaoui, Salma, Baradel, Fabien, Lucas, Thomas, Leroy, Vincent, Brégier, Romain, Weinzaepfel, Philippe, Rogez, Grégory
Human perception and understanding is a major domain of computer vision which, like many other vision subdomains recently, stands to gain from the use of large models pre-trained on large datasets. We hypothesize that the most common pre-training str
Externí odkaz:
http://arxiv.org/abs/2311.09104
Autor:
Swamy, Anilkumar, Leroy, Vincent, Weinzaepfel, Philippe, Baradel, Fabien, Galaaoui, Salma, Bregier, Romain, Armando, Matthieu, Franco, Jean-Sebastien, Rogez, Gregory
Recent hand-object interaction datasets show limited real object variability and rely on fitting the MANO parametric model to obtain groundtruth hand shapes. To go beyond these limitations and spur further research, we introduce the SHOWMe dataset wh
Externí odkaz:
http://arxiv.org/abs/2309.10748
Automatically producing instructions to modify one's posture could open the door to endless applications, such as personalized coaching and in-home physical therapy. Tackling the reverse problem (i.e., refining a 3D pose based on some natural languag
Externí odkaz:
http://arxiv.org/abs/2309.08480
Autor:
Armando, Matthieu, Boissieux, Laurence, Boyer, Edmond, Franco, Jean-Sebastien, Humenberger, Martin, Legras, Christophe, Leroy, Vincent, Marsot, Mathieu, Pansiot, Julien, Pujades, Sergi, Rekik, Rim, Rogez, Gregory, Swamy, Anilkumar, Wuhrer, Stefanie
This work presents 4DHumanOutfit, a new dataset of densely sampled spatio-temporal 4D human motion data of different actors, outfits and motions. The dataset is designed to contain different actors wearing different outfits while performing different
Externí odkaz:
http://arxiv.org/abs/2306.07399
Motivated by the increasing popularity of transformers in computer vision, in recent times there has been a rapid development of novel architectures. While in-domain performance follows a constant, upward trend, properties like robustness or uncertai
Externí odkaz:
http://arxiv.org/abs/2303.11298