GHOST 2.0实现高保真单张头像迁移，精准保留身份结构并融合背景。
GHOST 2.0: generative high-fidelity one shot transfer of heads
- 分阶段设计对齐与混合模块，多尺度保留身份特征
- 支持极端姿态变化，头发差异大时仍能自然融合
- 适合影视特效、虚拟形象生成等需要高质量头像迁移的场景
尽管人脸替换近年受到关注，头像替换这一相关任务仍鲜有研究。除肤色迁移外，头像替换还需在合成中保持头部整体结构信息，并修补替换头与背景间的缝隙。本文提出GHOST 2.0，包含两个专用模块：首先引入增强版对齐模型（Aligner），可在多尺度上保持身份信息，且对极端姿态变化具有鲁棒性；其次采用混合模块（Blender），通过肤色迁移和不匹配区域修复，将重演后的头像无缝融入目标背景。两个模块在对应任务上均优于基线，实现头像替换的最先进性能。我们还处理了源与目标发型差异较大的复杂情况。代码已开源。
原文摘要 · Abstract (English)
While the task of face swapping has recently gained attention in the research community, a related problem of head swapping remains largely unexplored. In addition to skin color transfer, head swap poses extra challenges, such as the need to preserve structural information of the whole head during synthesis and inpaint gaps between swapped head and background. In this paper, we address these concerns with GHOST 2.0, which consists of two problem-specific modules. First, we introduce enhanced Aligner model for head reenactment, which preserves identity information at multiple scales and is robust to extreme pose variations. Secondly, we use a Blender module that seamlessly integrates the reenacted head into the target background by transferring skin color and inpainting mismatched regions. Both modules outperform the baselines on the corresponding tasks, allowing to achieve state of the art results in head swapping. We also tackle complex cases, such as large difference in hair styles of source and target. Code is available at https://github.com/ai-forever/ghost-2.0
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。