Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This work was supported in part by National Key R&D Program under Grant 2021YFA1003000, in part by NSFC under Grant 125B2028, Grant 12125104, Grant 12426313, and Grant 12501709, and in part by the Fundamental Research Funds for the Central Universities, China under Grant xzy022025047. The authors are with the School of Mathematics and Statistics, Xi’an Jiaotong University, Shaanxi, P.R. China. E-mail: {tangxl, hexiaoyi, jiayixu}@stu.xjtu.edu.cn, {xianggu, jiansun}@xjtu.edu.cn. Code will be publicly available and updated at: https://github.com/xl-tang3/BaryIR. (Corresponding author: Jian Sun.)
1
0
2
1
Achieve robust all-in-one image restoration by learning a degradation-agnostic representation in Wasserstein space, enabling generalization to unseen and mixed real-world degradations.