2 papers
cs.CV2026
Efficient Sparse-to-Dense Visual Localization via Compact Gaussian Scene Representation and Accelerated Dense Pose Estimation
Zizhuo Li, Songchu Deng, Linfeng Tang +1
This letter presents LiteLoc, a novel and efficient localizer built on 3D Gaussian Splatting (3DGS). The previous state-of-the-art (SoTA) sparse-to-dense localizer, STDLoc, has sho…
cs.CV2025
DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching
Meng Yang, Fan Fan, Zizhuo Li +3
Multimodal image matching seeks pixel-level correspondences between images of different modalities, crucial for cross-modal perception, fusion and analysis. However, the significan…