5 papers
ER-Chord: Spatially Consistent One-Step Image Editing via Equal-Energy Reliability Redistribution
Peize Li, Hanzhen Zhao, Xingguo Xu +6
One-step generative models enable fast text-guided image editing, yet they often introduce unintended changes to regions that should remain unchanged. Temporal aggregation stabiliz…
TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification
Wanke Xia, Ruiding Zhu, Xingguo Xu +6
Multi-modal object re-identification exploits complementary RGB, near-infrared (NIR), and thermal-infrared (TIR) observations to retrieve target objects. However, existing methods…
Incentive Noise and Structural Prior Infusion for Multi-modal Object Re-Identification
Weixiang Zhou, Yuhao Wang, Xingguo Xu +4
Multi-modal object Re-Identification (ReID) benefits from complementary information across heterogeneous imaging modalities. To further enrich semantic representation, text descrip…
Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation
Weixiang Zhou, Xingguo Xu, Yuhao Wang +4
Multi-modal object Re-Identification (ReID) aims to retrieve target instances by leveraging complementary information across modalities. However, existing methods suffer from two c…
MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction
Peize Li, Fanhu Zeng, Tongda Xu +5
In-camera JPEG previews are ubiquitous in raw image formats and provide an sRGB reference at negligible storage cost. Although existing metadata-based reconstruction frameworks can…