[
    {
        "id": "osp-24453",
        "type": "article-journal",
        "title": "Mind the RefGAP: Correcting Reference Attention in Diffusion-Based Visual Editing",
        "author": [
            {
                "family": "Wang",
                "given": "Yanan"
            },
            {
                "family": "Liao",
                "given": "Shengcai"
            },
            {
                "family": "Liu",
                "given": "Guangyi"
            },
            {
                "family": "Liang",
                "given": "Xiaodan"
            }
        ],
        "URL": "https://omanscience.com/en/articles/mind-the-refgap-correcting-reference-attention-in-diffusion-based-visual-editing",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Reference-guided diffusion editors struggle to faithfully reproduce user-provided references. We identify a potential bottleneck in diffusion editors: many methods provide limited reference-attention allocation. For example, in LoomVideo, edit-region queries assign less than 1% of their attention mass to the reference. We introduce RefGAP, a training-free correction that determines logit-offset magnitudes online at each layer from the reference-attention mass measured during the forward pass. Positive offsets to reference logits strengthen reference usage by edit-region queries, while negative offsets for keep-region queries limit reference-induced changes outside the edit. Two global coefficients control the correction; they are selected once on validation data from four development diffusion editors and held fixed. Across seven diffusion-based image/video editors, RefGAP improves identity fidelity in head swapping and face swapping. RefGAP achieves a fidelity-preservation trade-off comparable to separately tuned constant edit-side biases, without per-approach strength sweeps. Additional experiments on virtual try-on and background replacement evaluate transfer beyond identity editing."
    }
]