用单张照片生成360度一致的人头视图，支持风格化与配饰。
DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis
- 基于DiffPortrait3D改进，加入控制网络和双外观模块保证前后一致。
- 在连续视角序列上训练，结合后方参考图像实现局部连续生成。
- 可生成高质量NeRF，适合沉浸式会议与个性化内容创作。
从单视角图像生成高质量人头360度视图，对实现可访问的沉浸式远程通信和可扩展的个性化内容创作至关重要。尽管当前先进方法能建模逼真人头，但最新的基于扩散模型的风格泛化头像生成方法仅限于正面视图，且存在视角不一致问题，难以转化为任意角度渲染的真实3D模型。我们提出一种新方法，可生成完全一致的360度头像视图，适用于真实人类、风格化及类人形态，包括眼镜、帽子等配件。该方法在DiffPortrait3D基础上引入定制ControlNet以生成后脑细节，并设计双外观模块确保全局前后一致性。通过在连续视角序列上训练并融合后方参考图像，实现鲁棒且局部连续的视图合成。所生成模型可用于构建高质量神经辐射场（NeRF），支持实时自由视角渲染，在对象生成与极难输入条件下的人头360度生成方面优于现有最优方法。
原文摘要 · Abstract (English)
Generating high-quality 360-degree views of human heads from single-view images is essential for enabling accessible immersive telepresence applications and scalable personalized content creation. While cutting-edge methods for full head generation are limited to modeling realistic human heads, the latest diffusion-based approaches for style-omniscient head synthesis can produce only frontal views and struggle with view consistency, preventing their conversion into true 3D models for rendering from arbitrary angles. We introduce a novel approach that generates fully consistent 360-degree head views, accommodating human, stylized, and anthropomorphic forms, including accessories like glasses and hats. Our method builds on the DiffPortrait3D framework, incorporating a custom ControlNet for back-of-head detail generation and a dual appearance module to ensure global front-back consistency. By training on continuous view sequences and integrating a back reference image, our approach achieves robust, locally continuous view synthesis. Our model can be used to produce high-quality neural radiance fields (NeRFs) for real-time, free-viewpoint rendering, outperforming state-of-the-art methods in object synthesis and 360-degree head generation for very challenging input portraits.
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。