PercHead：面向单图三维头部重建与编辑的感知头部模型
PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing
用 DINOv2 + SAM 2.1 特征构造的感知损失可直接替换 LPIPS/SSIM/L1，作为高频细节监督的通用手段；ViT 解耦 3D 表示与 2D 输入的架构也值得借鉴到单图重建任务。
原文依据 we rely on deep visual understanding of images and the resulting generalized supervision signals
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 PercHead，一个用于单图三维头部重建与解耦三维编辑的模型——这两项任务由于同一输入存在多种合理解释而本质上具有挑战性。本方法的核心是基于 DINOv2 与 SAM 2.1 的新型感知损失。与广泛采用的低层损失（如 LPIPS、结构相似度或 L1）不同，我们依赖对图像的深层视觉理解及其带来的泛化监督信号。我们表明，新损失可直接替换标准损失，并用于提升高频区域的视觉质量。模型架构基于视觉 Transformer（ViT），使我们能够将三维表示与二维输入解耦。我们在多视角图像上训练以保证视角一致性，并在野外图像上训练以获得对新环境的强迁移能力。本模型在新视角合成上取得最优性能，并且对极端视角表现出卓越的鲁棒性。我们还通过替换编码器并微调网络，将基础模型扩展至解耦三维编辑：由分割图控制几何，由文本提示词或参考图像指定外观。我们通过交互式图形界面展示了直观而强大的三维编辑能力。
英文原文摘要 1304 字符
We present PercHead, a model for single-image 3D head reconstruction and disentangled 3D editing - two tasks that are inherently challenging due to ambiguity in plausible explanations for the same input. At the heart of our approach lies our novel perceptual loss based on DINOv2 and SAM 2.1. Unlike widely-adopted low-level losses like LPIPS, SSIM or L1, we rely on deep visual understanding of images and the resulting generalized supervision signals. We show that our new loss can be a drop-in replacement for standard losses and used to improve visual quality in high-frequency areas. We base our model architecture on Vision Transformers (ViTs), allowing us to decouple the 3D representation from the 2D input. We train our method on multi-view images for view-consistency and in-the-wild images for strong transferability to new environments. Our model achieves state-of-the-art performance in novel-view synthesis and, furthermore, exhibits exceptional robustness to extreme viewing angles. We also extend our base model to disentangled 3D editing by swapping the encoder and fine-tuning the network. A segmentation map controls geometry and either a text prompt or a reference image specifies appearance. We highlight the intuitive and powerful 3D editing capabilities through an interactive GUI.