Zobrazeno 1 - 10
of 206
pro vyhledávání: '"Li, Chenxin"'
Recent advances in learning multi-modal representation have witnessed the success in biomedical domains. While established techniques enable handling multi-modal information, the challenges are posed when extended to various clinical modalities and p
Externí odkaz:
http://arxiv.org/abs/2407.05540
Recent advancements in large generative models and real-time neural rendering using point-based techniques pave the way for a future of widespread visual data distribution through sharing synthesized 3D assets. However, while standardized methods for
Externí odkaz:
http://arxiv.org/abs/2407.01301
Autor:
Li, Chenxin, Feng, Brandon Y., Liu, Yifan, Liu, Hengyu, Wang, Cheng, Yu, Weihao, Yuan, Yixuan
3D reconstruction of biological tissues from a collection of endoscopic images is a key to unlock various important downstream surgical applications with 3D capabilities. Existing methods employ various advanced neural rendering techniques for photor
Externí odkaz:
http://arxiv.org/abs/2407.01029
The advent of 3D Gaussian Splatting (3D-GS) techniques and their dynamic scene modeling variants, 4D-GS, offers promising prospects for real-time rendering of dynamic surgical scenarios. However, the prerequisite for modeling dynamic scenes by a larg
Externí odkaz:
http://arxiv.org/abs/2406.16073
U-Net has become a cornerstone in various visual applications such as image segmentation and diffusion probability models. While numerous innovative designs and improvements have been introduced by incorporating transformers or MLPs, the networks are
Externí odkaz:
http://arxiv.org/abs/2406.02918
Autor:
Li, Chenxin, Liu, Hengyu, Liu, Yifan, Feng, Brandon Y., Li, Wuyang, Liu, Xinyu, Chen, Zhen, Shao, Jing, Yuan, Yixuan
Generative models hold promise for revolutionizing medical education, robot-assisted surgery, and data augmentation for machine learning. Despite progress in generating 2D medical images, the complex domain of clinical video generation has largely re
Externí odkaz:
http://arxiv.org/abs/2403.11050
Reconstructing deformable tissues from endoscopic videos is essential in many downstream surgical applications. However, existing methods suffer from slow rendering speed, greatly limiting their practical use. In this paper, we introduce EndoGaussian
Externí odkaz:
http://arxiv.org/abs/2401.12561
Autor:
Rao, Zhijie, Guo, Jingcai, Lu, Xiaocheng, Zhou, Qihua, Zhang, Jie, Wei, Kang, Li, Chenxin, Guo, Song
Generalized Zero-shot Learning (GZSL) has yielded remarkable performance by designing a series of unbiased visual-semantics mappings, wherein, the precision relies heavily on the completeness of extracted visual features from both seen and unseen cla
Externí odkaz:
http://arxiv.org/abs/2311.14750
The accurate estimation of six degrees-of-freedom (6DoF) object poses is essential for many applications in robotics and augmented reality. However, existing methods for 6DoF pose estimation often depend on CAD templates or dense support views, restr
Externí odkaz:
http://arxiv.org/abs/2306.07598
Recent advances in neural rendering imply a future of widespread visual data distributions through sharing NeRF model weights. However, while common visual data (images and videos) have standard approaches to embed ownership or copyright information
Externí odkaz:
http://arxiv.org/abs/2212.01602