改进单目3D人脸建模的投影方式，让近景人脸更真实。
Revisiting an Old Perspective Projection for Monocular 3D Morphable Models Regression
- 用新参数模拟透视畸变，保留原有模型稳定性。
- 在头戴相机自拍数据上，重建精度显著提升。
- 适合做近距人脸动画或虚拟形象的开发者使用。
我们提出一种新型相机模型，用于单目3D形态模型（3DMM）回归，有效捕捉近距离人脸图像中的透视畸变。将3D形态模型拟合到视频是内容创作的关键技术，其中基于回归的方法通过匹配模型渲染输出与目标图像，实现了快速准确的结果。传统方法多采用正交投影，虽能消除焦距与物体距离的模糊性，但忽略了透视效应，导致在头戴式相机等近距拍摄场景中表现不佳。本文在正交投影基础上引入新的缩放参数，加入伪透视效果的同时保持原投影的稳定性。我们提出多种适配现有模型的微调技术，并在自建的头戴相机数据集上通过定量和定性对比验证了该方法的有效性。
原文摘要 · Abstract (English)
We introduce a novel camera model for monocular 3D Morphable Model (3DMM) regression methods that effectively captures the perspective distortion effect commonly seen in close-up facial images. Fitting 3D morphable models to video is a key technique in content creation. In particular, regression-based approaches have produced fast and accurate results by matching the rendered output of the morphable model to the target image. These methods typically achieve stable performance with orthographic projection, which eliminates the ambiguity between focal length and object distance. However, this simplification makes them unsuitable for close-up footage, such as that captured with head-mounted cameras. We extend orthographic projection with a new shrinkage parameter, incorporating a pseudo-perspective effect while preserving the stability of the original projection. We present several techniques that allow finetuning of existing models, and demonstrate the effectiveness of our modification through both quantitative and qualitative comparisons using a custom dataset recorded with head-mounted cameras.
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。