Zobrazeno 1 - 10
of 19 058
pro vyhledávání: '"LOY, A."'
This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise Predictio
Externí odkaz:
http://arxiv.org/abs/2412.09013
This study aims to achieve more precise and versatile object control in image-to-video (I2V) generation. Current methods typically represent the spatial movement of target objects with 2D trajectories, which often fail to capture user intention and f
Externí odkaz:
http://arxiv.org/abs/2412.07721
In this work, we introduce a single parameter $\omega$, to effectively control granularity in diffusion-based synthesis. This parameter is incorporated during the denoising steps of the diffusion model's reverse process. Our approach does not require
Externí odkaz:
http://arxiv.org/abs/2411.17769
Autor:
Lan, Yushi, Zhou, Shangchen, Lyu, Zhaoyang, Hong, Fangzhou, Yang, Shuai, Dai, Bo, Pan, Xingang, Loy, Chen Change
While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations. This paper introduces a novel 3D generation framework that addresses these challenges,
Externí odkaz:
http://arxiv.org/abs/2411.08033
Line art colorization plays a crucial role in hand-drawn animation production, where digital artists manually colorize segments using a paint bucket tool, guided by RGB values from character color design sheets. This process, often called paint bucke
Externí odkaz:
http://arxiv.org/abs/2410.19424
Autor:
Bombaerts, Gunter, Hannes, Tom, Adam, Martin, Aloisi, Alessandra, Anderson, Joel, Berger, Lawrence, Bettera, Stefano Davide, Campo, Enrico, Candiotto, Laura, Panizza, Silvia Caprioglio, Citton, Yves, DâAngelo, Diego, Dennis, Matthew, Depraz, Nathalie, Doran, Peter, Drechsler, Wolfgang, Duane, Bill, Edelglass, William, Eisenberger, Iris, McGuire, Beverley Foulks, Fredriksson, Antony, Gill, Karamjit S., Hershock, Peter D., Hongladarom, Soraj, Jacobs, Beth, Karsai, Gábor, Lennerfors, Thomas, Lim, Jeanne, Lin, Chien-Te, Losoncz, Mark, Loy, David, Marin, Lavinia, Marosán, Bence Péter, Mascarello, Chiara, McMahan, David, Park, Jin Y., Petek, Nina, Puzio, Anna, Schaubroek, Katrien, Schlieter, Jens, Schroeder, Brian, Shakya, Shobhit, Shi, Juewei, Solomonova, Elizaveta, Tormen, Francesco, Uttam, Jitendra, Van Vugt, Marieke, Vörös, Sebastjan, Wehrle, Maren, Wellner, Galit, Wirth, Jason M., Witkowski, Olaf, Wongkitrungrueng, Apiradee, Wright, Dale S., Zheng, Yutong
As the signatories of this manifesto, we denounce the attention economy as inhumane and a threat to our sociopolitical and ecological well-being. We endorse policymakers' efforts to address the negative consequences of the attention economy's technol
Externí odkaz:
http://arxiv.org/abs/2410.17421
Autor:
Jiang, Yuming, Zhao, Nanxuan, Liu, Qing, Singh, Krishna Kumar, Yang, Shuai, Loy, Chen Change, Liu, Ziwei
Group portrait editing is highly desirable since users constantly want to add a person, delete a person, or manipulate existing persons. It is also challenging due to the intricate dynamics of human interactions and the diverse gestures. In this work
Externí odkaz:
http://arxiv.org/abs/2409.14379
Autor:
Franceschi, Jonathan, Loy, Nadia
In this paper we introduce the optimal control of a kinetic model describing agents who migrate on a graph and interact within its nodes exchanging a physical quantity. As a prototype model, we consider the spread of an infectious disease on a graph,
Externí odkaz:
http://arxiv.org/abs/2409.13542
Despite the promising progress of face image super-resolution, video face super-resolution remains relatively under-explored. Existing approaches either adapt general video super-resolution networks to face datasets or apply established face image su
Externí odkaz:
http://arxiv.org/abs/2408.05205
Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-cl
Externí odkaz:
http://arxiv.org/abs/2407.09842