4 papers
Hybrid Fusion: One-Minute Efficient Training for Zero-Shot Cross-Domain Image Fusion
Ran Zhang, Xuanhua He, Liu Liu
Image fusion seeks to integrate complementary information from multiple sources into a single, superior image. While traditional methods are fast, they lack adaptability and perfor…
Rethinking Pan-sharpening: A New Training Process for Full-Resolution Generalization
Ran Zhang, Xuanhua He, Li Xueheng +6
The field of pan-sharpening has recently seen a trend towards increasingly large and complex models, often trained on single, specific satellite datasets. This one-dataset, one-mod…
KineDiff3D: Kinematic-Aware Diffusion for Category-Level Articulated Object Shape Reconstruction and Generation
WenBo Xu, Liu Liu, Li Zhang +4
Articulated objects, such as laptops and drawers, exhibit significant challenges for 3D reconstruction and pose estimation due to their multi-part geometries and variable joint con…
Distilling Textual Priors from LLM to Efficient Image Fusion
Ran Zhang, Xuanhua He, Ke Cao +4
Multi-modality image fusion aims to synthesize a single, comprehensive image from multiple source inputs. Traditional approaches, such as CNNs and GANs, offer efficiency but strugg…