面向工业应用的基于色度键控的高保真头部融合研究
Towards High-fidelity Head Blending with Chroma Keying for Industrial Applications
AI总结:
针对数字内容创作中头部无缝融合的伪影问题,提出解耦背景合成与前景融合的CHANGER流水线,结合色度键控、$H^2$增强与FPAT模块,实现了优于现有方法的高保真工业级头部融合效果。
摘要:
我们提出了一套工业级头部融合流水线,用于数字内容创作中将演员头部无缝合成到目标身体上的任务。核心挑战源于头部形状与头发结构的差异,会导致边界不自然与融合伪影。现有方法将前景与背景视为单一任务处理,造成融合质量欠佳。为解决该问题,我们提出CHANGER——一种将背景合成与前景融合解耦的新型流水线。通过利用色度键控生成无伪影的背景,并引入头部形状与长发增强($H^2$ 增强)来模拟各类头型与发型,CHANGER提升了在海量多样真实场景下的泛化能力。此外,我们的前景预测注意力Transformer(FPAT)模块通过预测并聚焦头身关键区域,优化了前景融合效果。在基准数据集上的定量与定性评估表明,CHANGER性能优于当前最优方法,可生成高保真的工业级结果。
英文摘要:
We introduce an industrial Head Blending pipeline for the task of seamlessly integrating an actor's head onto a target body in digital content creation. The key challenge stems from discrepancies in head shape and hair structure, which lead to unnatural boundaries and blending artifacts. Existing methods treat foreground and background as a single task, resulting in suboptimal blending quality. To address this problem, we propose CHANGER, a novel pipeline that decouples background integration from foreground blending. By utilizing chroma keying for artifact-free background generation and introducing Head shape and long Hair augmentation ($H^2$ augmentation) to simulate a wide range of head shapes and hair styles, CHANGER improves generalization on innumerable various real-world cases. Furthermore, our Foreground Predictive Attention Transformer (FPAT) module enhances foreground blending by predicting and focusing on key head and body regions. Quantitative and qualitative evaluations on benchmark datasets demonstrate that our CHANGER outperforms state-of-the-art methods, delivering high-fidelity, industrial-grade results.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。