Zobrazeno 1 - 10
of 3 732
pro vyhledávání: '"Harandi, A."'
A novel physics-informed operator learning technique based on spectral methods is introduced to model the complex behavior of heterogeneous materials. The Lippmann-Schwinger operator in Fourier space is employed to construct physical constraints with
Externí odkaz:
http://arxiv.org/abs/2410.19027
With 3D Gaussian Splatting (3DGS) advancing real-time and high-fidelity rendering for novel view synthesis, storage requirements pose challenges for their widespread adoption. Although various compression techniques have been proposed, previous art s
Externí odkaz:
http://arxiv.org/abs/2410.08017
Despite their high accuracy, complex neural networks demand significant computational resources, posing challenges for deployment on resource-constrained devices such as mobile phones and embedded systems. Compression algorithms have been developed t
Externí odkaz:
http://arxiv.org/abs/2409.03555
Implicit Neural Representations (INRs) have recently advanced the field of deep learning due to their ability to learn continuous representations of signals without the need for large training datasets. Although INR methods have been studied for medi
Externí odkaz:
http://arxiv.org/abs/2409.01013
Autor:
Li, Pengxiang, Gao, Zhi, Zhang, Bofei, Yuan, Tao, Wu, Yuwei, Harandi, Mehrtash, Jia, Yunde, Zhu, Song-Chun, Li, Qing
Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derive
Externí odkaz:
http://arxiv.org/abs/2407.11522
Stabilization of a quadrotor without a controller based on cascade structure is a challenging problem. Besides, due to the dynamics and the number of underactuation, an energy shaping controller has not been designed in 3D for a quadrotor. This paper
Externí odkaz:
http://arxiv.org/abs/2406.07682
Publikováno v:
CVPR 2024
In recent years, Neural Radiance Field (NeRF) has demonstrated remarkable capabilities in representing 3D scenes. To expedite the rendering process, learnable explicit representations have been introduced for combination with implicit NeRF representa
Externí odkaz:
http://arxiv.org/abs/2406.04101
Autor:
Yamazaki, Yusuke, Harandi, Ali, Muramatsu, Mayu, Viardin, Alexandre, Apel, Markus, Brepols, Tim, Reese, Stefanie, Rezaei, Shahed
Publikováno v:
Eng. Comput., 1-29 (2024)
We propose a novel finite element-based physics-informed operator learning framework that allows for predicting spatiotemporal dynamics governed by partial differential equations (PDEs). The proposed framework employs a loss function inspired by the
Externí odkaz:
http://arxiv.org/abs/2405.12465
Autor:
Rezaei, Shahed, Asl, Reza Najian, Faroughi, Shirko, Asgharzadeh, Mahdi, Harandi, Ali, Koopas, Rasoul Najafi, Laschet, Gottfried, Reese, Stefanie, Apel, Markus
To obtain fast solutions for governing physical equations in solid mechanics, we introduce a method that integrates the core ideas of the finite element method with physics-informed neural networks and concept of neural operators. This approach gener
Externí odkaz:
http://arxiv.org/abs/2404.00074
Autor:
Wang, Yanshuo, Cheraghian, Ali, Hayder, Zeeshan, Hong, Jie, Ramasinghe, Sameera, Rahman, Shafin, Ahmedt-Aristizabal, David, Li, Xuesong, Petersson, Lars, Harandi, Mehrtash
Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test-Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches to handle t
Externí odkaz:
http://arxiv.org/abs/2403.18442