Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Paschalidou, Despoina"'
Reconstructing dynamic scenes from image inputs is a fundamental computer vision task with many downstream applications. Despite recent advancements, existing approaches still struggle to achieve high-quality reconstructions from unseen viewpoints an
Externí odkaz:
http://arxiv.org/abs/2411.00705
The increased demand for tools that automate the 3D content creation process led to tremendous progress in deep generative models that can generate diverse 3D objects of high fidelity. In this paper, we present PASTA, an autoregressive transformer ar
Externí odkaz:
http://arxiv.org/abs/2407.13677
Autor:
Ugrinovic, Nicolas, Pan, Boxiao, Pavlakos, Georgios, Paschalidou, Despoina, Shen, Bokui, Sanchez-Riera, Jordi, Moreno-Noguer, Francesc, Guibas, Leonidas
We introduce MultiPhys, a method designed for recovering multi-person motion from monocular videos. Our focus lies in capturing coherent spatial placement between pairs of individuals across varying degrees of engagement. MultiPhys, being physically
Externí odkaz:
http://arxiv.org/abs/2404.11987
Autor:
Wan, Ziyu, Paschalidou, Despoina, Huang, Ian, Liu, Hongyu, Shen, Bokui, Xiang, Xiaoyu, Liao, Jing, Guibas, Leonidas
The increased demand for 3D data in AR/VR, robotics and gaming applications, gave rise to powerful generative pipelines capable of synthesizing high-quality 3D objects. Most of these models rely on the Score Distillation Sampling (SDS) algorithm to o
Externí odkaz:
http://arxiv.org/abs/2312.06663
Autor:
Kim, Kunho, Uy, Mikaela Angelina, Paschalidou, Despoina, Jacobson, Alec, Guibas, Leonidas J., Sung, Minhyuk
We propose OptCtrlPoints, a data-driven framework designed to identify the optimal sparse set of control points for reproducing target shapes using biharmonic 3D shape deformation. Control-point-based 3D deformation methods are widely utilized for in
Externí odkaz:
http://arxiv.org/abs/2309.12899
Autor:
Bahmani, Sherwin, Park, Jeong Joon, Paschalidou, Despoina, Yan, Xingguang, Wetzstein, Gordon, Guibas, Leonidas, Tagliasacchi, Andrea
In this work, we introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts, trained using single-view images. Different from most existing 3D GANs that limit their applicability to alig
Externí odkaz:
http://arxiv.org/abs/2303.12074
Autor:
Stearns, Colton, Rempe, Davis, Liu, Jiateng, Fu, Alex, Mascha, Sebastien, Park, Jeong Joon, Paschalidou, Despoina, Guibas, Leonidas J.
Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene, resulting in a point cloud with notable 1D curve-like structures. In this work, we introduce a new point cloud processing scheme and backbone, called CurveCloudNet,
Externí odkaz:
http://arxiv.org/abs/2303.12050
Autor:
Tertikas, Konstantinos, Paschalidou, Despoina, Pan, Boxiao, Park, Jeong Joon, Uy, Mikaela Angelina, Emiris, Ioannis, Avrithis, Yannis, Guibas, Leonidas
Impressive progress in generative models and implicit representations gave rise to methods that can generate 3D shapes of high quality. However, being able to locally control and edit shapes is another essential property that can unlock several conte
Externí odkaz:
http://arxiv.org/abs/2303.09554
Autor:
Wang, Zhen, Zhou, Shijie, Park, Jeong Joon, Paschalidou, Despoina, You, Suya, Wetzstein, Gordon, Guibas, Leonidas, Kadambi, Achuta
This work introduces alternating latent topologies (ALTO) for high-fidelity reconstruction of implicit 3D surfaces from noisy point clouds. Previous work identifies that the spatial arrangement of latent encodings is important to recover detail. One
Externí odkaz:
http://arxiv.org/abs/2212.04096
Autor:
Pan, Boxiao, Shen, Bokui, Rempe, Davis, Paschalidou, Despoina, Mo, Kaichun, Yang, Yanchao, Guibas, Leonidas J.
The ability to forecast human-environment collisions from egocentric observations is vital to enable collision avoidance in applications such as VR, AR, and wearable assistive robotics. In this work, we introduce the challenging problem of predicting
Externí odkaz:
http://arxiv.org/abs/2210.01781