Zobrazeno 1 - 10
of 2 893
pro vyhledávání: '"Samaras, A. P."'
Developing robots that can assist humans efficiently, safely, and adaptively is crucial for real-world applications such as healthcare. While previous work often assumes a centralized system for co-optimizing human-robot interactions, we argue that r
Externí odkaz:
http://arxiv.org/abs/2412.11913
Autor:
Xu, Meilong, Gupta, Saumya, Hu, Xiaoling, Li, Chen, Abousamra, Shahira, Samaras, Dimitris, Prasanna, Prateek, Chen, Chao
Accurately modeling multi-class cell topology is crucial in digital pathology, as it provides critical insights into tissue structure and pathology. The synthetic generation of cell topology enables realistic simulations of complex tissue environment
Externí odkaz:
http://arxiv.org/abs/2412.06011
Autor:
Belagali, Varun, Yellapragada, Srikar, Graikos, Alexandros, Kapse, Saarthak, Li, Zilinghan, Nandi, Tarak Nath, Madduri, Ravi K, Prasanna, Prateek, Saltz, Joel, Samaras, Dimitris
Self-supervised learning (SSL) methods have emerged as strong visual representation learners by training an image encoder to maximize similarity between features of different views of the same image. To perform this view-invariance task, current SSL
Externí odkaz:
http://arxiv.org/abs/2412.01672
Autor:
Zhang, Jingwei, Nguyen, Anh Tien, Han, Xi, Trinh, Vincent Quoc-Huy, Qin, Hong, Samaras, Dimitris, Hosseini, Mahdi S.
Efficiently modeling large 2D contexts is essential for various fields including Giga-Pixel Whole Slide Imaging (WSI) and remote sensing. Transformer-based models offer high parallelism but face challenges due to their quadratic complexity for handli
Externí odkaz:
http://arxiv.org/abs/2412.00678
Current methods for extracting intrinsic image components, such as reflectance and shading, primarily rely on statistical priors. These methods focus mainly on simple synthetic scenes and isolated objects and struggle to perform well on challenging r
Externí odkaz:
http://arxiv.org/abs/2411.17235
Autor:
Yellapragada, Srikar, Graikos, Alexandros, Triaridis, Kostas, Prasanna, Prateek, Gupta, Rajarsi R., Saltz, Joel, Samaras, Dimitris
Diffusion models have revolutionized image generation, yet several challenges restrict their application to large-image domains, such as digital pathology and satellite imagery. Given that it is infeasible to directly train a model on 'whole' images
Externí odkaz:
http://arxiv.org/abs/2411.16969
Diffusion models excel at high-quality image and video generation. However, a major drawback is their high latency. A simple yet powerful way to speed them up is by merging similar tokens for faster computation, though this can result in some quality
Externí odkaz:
http://arxiv.org/abs/2411.16720
It has been proposed that if the gravitational constant $G$ abruptly decreased around 130 Myr ago, then Type Ia supernovae (SNe) in the Hubble flow would have a different luminosity to those in host galaxies with Cepheid distances. This would make Hu
Externí odkaz:
http://arxiv.org/abs/2411.15301
Recent works on Generalized Referring Expression Segmentation (GRES) struggle with handling complex expressions referring to multiple distinct objects. This is because these methods typically employ an end-to-end foreground-background segmentation an
Externí odkaz:
http://arxiv.org/abs/2411.15087
Autor:
Wu, Haoyu, Karumuri, Meher Gitika, Zou, Chuhang, Bang, Seungbae, Li, Yuelong, Samaras, Dimitris, Hadap, Sunil
Current image-to-3D approaches suffer from high computational costs and lack scalability for high-resolution outputs. In contrast, we introduce a novel framework to directly generate explicit surface geometry and texture using multi-view 2D depth and
Externí odkaz:
http://arxiv.org/abs/2411.10947