Zobrazeno 1 - 10
of 312 339
pro vyhledávání: '"Pang, A."'
Autor:
Wu, Feize, Pang, Yun, Zhang, Junyi, Pang, Lianyu, Yin, Jian, Zhao, Baoquan, Li, Qing, Mao, Xudong
Recent advances in text-to-image personalization have enabled high-quality and controllable image synthesis for user-provided concepts. However, existing methods still struggle to balance identity preservation with text alignment. Our approach is bas
Externí odkaz:
http://arxiv.org/abs/2408.15914
Cone Beam Computed Tomography (CBCT) finds diverse applications in medicine. Ensuring high image quality in CBCT scans is essential for accurate diagnosis and treatment delivery. Yet, the susceptibility of CBCT images to noise and artifacts undermine
Externí odkaz:
http://arxiv.org/abs/2409.18355
Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness
Externí odkaz:
http://arxiv.org/abs/2409.18125
The content of a webpage described or posted an event in the cyberspace inevitably reflects viewpoints, values and trends of the physical society. Mapping an event on web to the popularity score plays a pivot role to sense the social trends from the
Externí odkaz:
http://arxiv.org/abs/2409.17678
We present \textbf{Disco4D}, a novel Gaussian Splatting framework for 4D human generation and animation from a single image. Different from existing methods, Disco4D distinctively disentangles clothings (with Gaussian models) from the human body (wit
Externí odkaz:
http://arxiv.org/abs/2409.17280
Autor:
Pang, Khang Ee
The classical no-slip boundary condition of the Navier-Stokes equations fails to describe the spreading motion of a droplet on a substrate due to the missing small-scale physics near the contact line. In this thesis, we introduce a novel regularizati
Externí odkaz:
http://arxiv.org/abs/2409.17187
We study behavior change-based visual risk object identification (Visual-ROI), a critical framework designed to detect potential hazards for intelligent driving systems. Existing methods often show significant limitations in spatial accuracy and temp
Externí odkaz:
http://arxiv.org/abs/2409.15846
Autor:
Ma, Jun, Wang, Meng, Pang, Jinhui, Wang, Haofen, Feng, Xuejing, Hu, Zhipeng, Yang, Zhenyu, Guo, Mingyang, Liu, Zhenming, Wang, Junwei, Lu, Siyi, Gou, Zhiming
The development of Artificial Intelligence (AI) Large Models has a great impact on the application development of automotive Intelligent cockpit. The fusion development of Intelligent Cockpit and Large Models has become a new growth point of user exp
Externí odkaz:
http://arxiv.org/abs/2409.15795
We present the first example of an interacting Carroll supersymmetric field theory with both temporal and spatial derivatives, belonging to the Galileon class, where the non-linear field equation remains second-order in derivative. To achieve this, w
Externí odkaz:
http://arxiv.org/abs/2409.15428
We introduce a novel gene regulatory network (GRN) inference method that integrates optimal transport (OT) with a deep-learning structural inference model. Advances in next-generation sequencing enable detailed yet destructive gene expression assays
Externí odkaz:
http://arxiv.org/abs/2409.15080