3 papers
cs.CV2025
Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting
Hanzhou Liu, Jia Huang, Mi Lu +2
We present Stylos, a single-forward 3D Gaussian framework for 3D style transfer that operates on unposed content, from a single image to a multi-view collection, conditioned on a s…
cs.CV2025
DiNAT-IR: Exploring Dilated Neighborhood Attention for High-Quality Image Restoration
Hanzhou Liu, Binghan Li, Chengkai Liu +1
Transformers, with their self-attention mechanisms for modeling long-range dependencies, have become a dominant paradigm in image restoration tasks. However, the high computational…
cs.CV2024
XYScanNet: A State Space Model for Single Image Deblurring
Hanzhou Liu, Chengkai Liu, Jiacong Xu +2
Deep state-space models (SSMs), like recent Mamba architectures, are emerging as a promising alternative to CNN and Transformer networks. Existing Mamba-based restoration methods p…