High-quality image editing requires precise modification of target regions while preserving the content of unrelated regions. Existing editing models produce flattened outputs that limit precise local manipulation and layer reuse, while decomposition methods typically optimize layer recovery separately from instruction...
Wen Xue, Yong Liu, Xue-Heng Li et al.· 0 citations
FreeShadow is proposed, a training-free shadow removal method built upon pretrained diffusion models, which exploits diffusion priors for shadow removal without any training or optimization.
Yi-Nan Wang, Yan Huang, Yong Xu et al.· arXiv.org· 0 citations
DIGEST is proposed, a multi-graph framework that propagates trainable ID embeddings on a denoised user—item graph and a fused modality-induced item—item graph, and interleaves message passing with dynamic graph refinement that iteratively reweights existing edges to suppress noisy connections.
Xiangyu Sai, M. Madadi, Sergio Escalera et al.· Annual International ACM SIG...· 0 citations
A two-stage framework integrating degradation-aware self-supervised contrastive pre-training with frequency-spatial domain feature learning is proposed, offering a reliable solution for NR-IQA in real-world multimedia systems and advancing the alignment between computational quality assessment and human visual percepti...
Li-Tao Duan, Yan Huang, Yong Xu et al.· The Visual Computer· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
