面向3D感知深度生成模型的高效少样本身份保持属性编辑
Efficient Few-shot Identity Preserving Attribute Editing for 3D-aware Deep Generative Models
AI总结：
本研究针对3D人脸身份保持属性编辑的挑战，结合3D感知生成模型与2D编辑技术，仅需10张以内标注样本即可估计潜在空间编辑方向，还验证了编辑线性性并探究了3D一致的人脸老化风格流形。
摘要：
人脸身份保持编辑是一类生成任务，可在保留人脸身份的前提下修改光照、添加/移除眼镜、实现人脸老化、编辑发型、调整表情等。2D生成模型的最新进展已能利用GAN的组合性，通过简单技术实现照片级真实的人脸编辑。然而，针对具备给定属性集的3D人脸开展身份保持编辑是一项具有挑战性的任务，因为生成模型必须从多个姿态推理视角一致性，并渲染出逼真的3D人脸。此外，3D人像编辑需要大规模带属性标注的数据集，且存在低分辨率下可编辑性与高分辨率下编辑灵活性不足的权衡问题。在本研究中，我们旨在通过识别对应于照片级真实编辑的潜在空间方向，缓解3D人脸编辑中的部分约束。为解决该问题，我们提出了一种方法，该方法基于3D感知深度生成模型和2D人像编辑技术的最新进展，为3D感知生成模型实现高效的少样本身份保持属性编辑。我们的实验结果旨在证明，仅使用10张或更少的某属性标注图像，就足以估计出对应于3D感知属性编辑的潜在空间编辑方向。本研究中，我们利用一个带掩码的现有面部数据集来获取合成图像，以满足估计编辑方向所需的少量属性样本需求。此外，为验证编辑的线性特性，我们通过执行顺序编辑探究了单样本风格化，并使用（2D）Attribute Style Manipulation（ASM，属性风格操控）技术探究了用于3D一致身份保持人脸老化的连续风格流形。代码和结果可访问：https://vishal-vinod.github.io/gmpi-edit/
英文摘要：
Identity preserving editing of faces is a generative task that enables modifying the illumination, adding/removing eyeglasses, face aging, editing hairstyles, modifying expression etc., while preserving the identity of the face. Recent progress in 2D generative models have enabled photorealistic editing of faces using simple techniques leveraging the compositionality in GANs. However, identity preserving editing for 3D faces with a given set of attributes is a challenging task as the generative model must reason about view consistency from multiple poses and render a realistic 3D face. Further, 3D portrait editing requires large-scale attribute labelled datasets and presents a trade-off between editability in low-resolution and inflexibility to editing in high resolution. In this work, we aim to alleviate some of the constraints in editing 3D faces by identifying latent space directions that correspond to photorealistic edits. To address this, we present a method that builds on recent advancements in 3D-aware deep generative models and 2D portrait editing techniques to perform efficient few-shot identity preserving attribute editing for 3D-aware generative models. We aim to show from experimental results that using just ten or fewer labelled images of an attribute is sufficient to estimate edit directions in the latent space that correspond to 3D-aware attribute editing. In this work, we leverage an existing face dataset with masks to obtain the synthetic images for few attribute examples required for estimating the edit directions. Further, to demonstrate the linearity of edits, we investigate one-shot stylization by performing sequential editing and use the (2D) Attribute Style Manipulation (ASM) technique to investigate a continuous style manifold for 3D consistent identity preserving face aging. Code and results are available at: https://vishal-vinod.github.io/gmpi-edit/
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。
