Zobrazeno 1 - 10
of 1 214
pro vyhledávání: '"P. Planché"'
Autor:
Ding, Hao, Gao, Zhongpai, Planche, Benjamin, Luan, Tianyu, Sharma, Abhishek, Zheng, Meng, Lou, Ange, Chen, Terrence, Unberath, Mathias, Wu, Ziyan
Surgical phase recognition is essential for analyzing procedure-specific surgical videos. While recent transformer-based architectures have advanced sequence processing capabilities, they struggle with maintaining consistency across lengthy surgical
Externí odkaz:
http://arxiv.org/abs/2411.18018
Autor:
Deng, Andong, Gao, Zhongpai, Choudhuri, Anwesa, Planche, Benjamin, Zheng, Meng, Wang, Bin, Chen, Terrence, Chen, Chen, Wu, Ziyan
Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning and temporal video grounding in a unified system. However, the scarcity
Externí odkaz:
http://arxiv.org/abs/2411.16932
Autor:
Lou, Ange, Planche, Benjamin, Gao, Zhongpai, Li, Yamin, Luan, Tianyu, Ding, Hao, Zheng, Meng, Chen, Terrence, Wu, Ziyan, Noble, Jack
Numerous recent approaches to modeling and re-rendering dynamic scenes leverage plane-based explicit representations, addressing slow training times associated with models like neural radiance fields (NeRF) and Gaussian splatting (GS). However, merel
Externí odkaz:
http://arxiv.org/abs/2410.14169
Autor:
Wang, Bin, Choudhuri, Anwesa, Zheng, Meng, Gao, Zhongpai, Planche, Benjamin, Deng, Andong, Liu, Qin, Chen, Terrence, Bagci, Ulas, Wu, Ziyan
Interactive segmentation aims to accurately segment target objects with minimal user interactions. However, current methods often fail to accurately separate target objects from the background, due to a limited understanding of order, the relative de
Externí odkaz:
http://arxiv.org/abs/2410.12214
Autor:
Peng, Qucheng, Planche, Benjamin, Gao, Zhongpai, Zheng, Meng, Choudhuri, Anwesa, Chen, Terrence, Chen, Chen, Wu, Ziyan
Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality. However, cu
Externí odkaz:
http://arxiv.org/abs/2410.07577
Novel view synthesis has advanced significantly with the development of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS). However, achieving high quality without compromising real-time rendering remains challenging, particularly for phy
Externí odkaz:
http://arxiv.org/abs/2410.04974
Conventional 3D medical image segmentation methods typically require learning heavy 3D networks (e.g., 3D-UNet), as well as large amounts of in-domain data with accurate pixel/voxel-level labels to avoid overfitting. These solutions are thus extremel
Externí odkaz:
http://arxiv.org/abs/2408.14427
Positioning patients for scanning and interventional procedures is a critical task that requires high precision and accuracy. The conventional workflow involves manually adjusting the patient support to align the center of the target body part with t
Externí odkaz:
http://arxiv.org/abs/2407.14903
Autor:
Luan, Tianyu, Gao, Zhongpai, Xie, Luyuan, Sharma, Abhishek, Ding, Hao, Planche, Benjamin, Zheng, Meng, Lou, Ange, Chen, Terrence, Yuan, Junsong, Wu, Ziyan
We introduce a novel bottom-up approach for human body mesh reconstruction, specifically designed to address the challenges posed by partial visibility and occlusion in input images. Traditional top-down methods, relying on whole-body parametric mode
Externí odkaz:
http://arxiv.org/abs/2407.09694
Digitally reconstructed radiographs (DRRs) are simulated 2D X-ray images generated from 3D CT volumes, widely used in preoperative settings but limited in intraoperative applications due to computational bottlenecks, especially for accurate but heavy
Externí odkaz:
http://arxiv.org/abs/2406.02518