Jiang Zhou

Spectrally Pruned Gaussian Fields with Neural Compensation

2024 · arXiv (Cornell University)

Recently, 3D Gaussian Splatting, as a novel 3D representation, has garnered attention for its fast rendering speed and high rendering quality. However, this comes with high memory consumption, e.g., a well-trained Gaussian field may utilize …

Tackling Feature Skew in Heterogeneous Federated Learning with Semantic Enhancement

2024

A critical challenge in federated learning is data heterogeneity, compounded by varying local data distribution, thereby significantly impacting the performance of both local and global models. Prior works struggle to effectively address data heterogeneity but …