8 papers · 1 filter
Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentation
Xingyue Zhao, Wenke Huang, Linghao Zhuang +11
Federated learning enables medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains challenging. Exis…
Orthogonal Spatial-temporal Distributional Transfer for 4D Generation
Wei Liu, Shengqiong Wu, Bobo Li +4
In the AIGC era, generating high-quality 4D content has garnered increasing research attention. Unfortunately, current 4D synthesis research is severely constrained by the lack of…
Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints
Lijun Guo, Haoyu Zhao, Xingyue Zhao +5
Building high-fidelity digital twins of articulated objects from visual data remains a central challenge. Existing approaches depend on multi-view captures of the object in discret…
Moving Light Adaptive Colonoscopy Reconstruction via Illumination-Attenuation-Aware 3D Gaussian Splatting
Hao Wang, Ying Zhou, Haoyu Zhao +5
3D Gaussian Splatting (3DGS) enables real-time view synthesis in colonoscopy but assumes static illumination, making it incompatible with the strong photometric variations caused b…
pFedSAM: Personalized Federated Learning of Segment Anything Model for Medical Image Segmentation
Tong Wang, Xingyue Zhao, Linghao Zhuang +5
Medical image segmentation is crucial for computer-aided diagnosis, yet privacy constraints hinder data sharing across institutions. Federated learning addresses this limitation, b…
Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting
Haoyu Zhao, Hao Wang, Xingyue Zhao +4
Recent advancements in 3D generation models have opened new possibilities for simulating dynamic 3D object movements and customizing behaviors, yet creating this content remains ch…
Topology-aware Human Avatars with Semantically-guided Gaussian Splatting
Haoyu Zhao, Chen Yang, Hao Wang +2
Reconstructing photo-realistic and topology-aware animatable human avatars from monocular videos remains challenging in computer vision and graphics. Recently, methods using 3D Gau…
3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning
Haoyu Zhao, Hao Wang, Chen Yang +1
Existing approaches for human avatar generation--both NeRF-based and 3D Gaussian Splatting (3DGS) based--struggle with maintaining 3D consistency and exhibit degraded detail recons…