Zobrazeno 1 - 10
of 393
pro vyhledávání: '"Cani, Marie‐Paule"'
Autor:
Andreou, Nefeli, Wang, Xi, Abrevaya, Victoria Fernández, Cani, Marie-Paule, Chrysanthou, Yiorgos, Kalogeiton, Vicky
Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align text and motion latent spaces but sacrifice expressiveness; others rely
Externí odkaz:
http://arxiv.org/abs/2410.14508
Autor:
Wang, Xi, Dufour, Nicolas, Andreou, Nefeli, Cani, Marie-Paule, Abrevaya, Victoria Fernandez, Picard, David, Kalogeiton, Vicky
Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models. It operates by combining the conditional and unconditional predictions using a fixed weight. However, recent works vary the weights through
Externí odkaz:
http://arxiv.org/abs/2404.13040
Publikováno v:
IEEE Transaction on Image Processing 2022
We present See360, which is a versatile and efficient framework for 360 panoramic view interpolation using latent space viewpoint estimation. Most of the existing view rendering approaches only focus on indoor or synthetic 3D environments and render
Externí odkaz:
http://arxiv.org/abs/2401.03431
Crowd simulation is important for video-games design, since it enables to populate virtual worlds with autonomous avatars that navigate in a human-like manner. Reinforcement learning has shown great potential in simulating virtual crowds, but the des
Externí odkaz:
http://arxiv.org/abs/2309.12841
The discounting mechanism in Reinforcement Learning determines the relative importance of future and present rewards. While exponential discounting is widely used in practice, non-exponential discounting methods that align with human behavior are oft
Externí odkaz:
http://arxiv.org/abs/2302.05740
Publikováno v:
Frontiers in Virtual Reality, Frontiers, 2022, 3
When we move on snow, sand, or mud, the ground deforms under our feet, immediately affecting our gait. We propose a physically based model for computing such interactions in real time, from only the kinematic motion of a virtual character. The force
Externí odkaz:
http://arxiv.org/abs/2209.10215
Publikováno v:
Computer Graphics Forum, Wiley, 2022, 41 (8)
Real-time character animation in dynamic environments requires the generation of plausible upper-body movements regardless of the nature of the environment, including non-rigid obstacles such as vegetation. We propose a flexible model for upper-body
Externí odkaz:
http://arxiv.org/abs/2209.10214
Simulating trajectories of virtual crowds is a commonly encountered task in Computer Graphics. Several recent works have applied Reinforcement Learning methods to animate virtual agents, however they often make different design choices when it comes
Externí odkaz:
http://arxiv.org/abs/2209.09344