This work takes a source-centric perspective on VAR editing, in which the encoded source image tokens serve as the primary visual state and the editing process focuses on condition-induced changes, and proposes EditMod, which compares source- and target-conditioned predictions under a shared autoregressive context.
Hongyi Fang, Chu-Wen Xie, Ben-Jia Zhou et al.· 0 citations
Qualitative analysis suggests that PatchHead reduces class-conditional domain discrepancy, and redirects the representation from content-dominated saliency toward spatially distributed authenticity evidence, which provides a representation-level account of why spatial patch aggregation transfers more reliably across ge...
Sheng-Bo Qi, Hongyi Fang, Ben-Jia Zhou et al.· 0 citations
Experimental results show that training with Human4K consistently improves whole-body reconstruction on standard benchmarks, with particularly large gains for hands, feet and depth-ambiguous limb configurations.
Tianshun Han, Ziyu Shi, Lijiang Liu et al.· arXiv.org· 0 citations
Experimental results show that K2N remains competitive with the VARSR baseline on standard SR metrics, while exhibiting clearer advantages on hallucination-focused evaluation, and suggest that explicitly rethinking the generation path in a scale-wise manner can be a promising direction for improving the reliability of...
Hongyi Fang, Jiahui Wu, Yichen Yue et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
