## 论文概要
**研究领域**: CV
**作者**: Umut Kocasari, Simon Giebenhain, Richard Shaw, Matthias Nießner
**发布时间**: 2026-04-21
**arXiv**: [2604.19702](https://arxiv.org/abs/2604.19702)
## 中文摘要
从图像序列中准确重建与跟踪动态人脸具有挑战性,因非刚性形变、表情变化与视角变化同时发生,在几何与对应关系估计中造成显著歧义。我们提出一种基于规范面部点预测的高保真四维面部重建统一方法,该表示为每个像素分配共享规范空间中的归一化面部坐标。此表述将密集跟踪与动态重建转化为规范重建问题,使单一前馈模型内实现时序一致几何与可靠对应关系。通过联合预测深度与规范坐标,我们的方法在单一架构内实现准确深度估计、时序稳定重建、密集三维几何与鲁棒面部点跟踪。我们使用基于 Transformer 的模型实现此表述,联合预测深度与规范面部坐标,使用多视角几何数据训练,非刚性扭曲至规范空间。图像与视频基准上的大量实验展示了在重建与跟踪任务上的最优性能,对应误差约为先前动态重建方法的 1/3,推理更快,深度准确率提升 16%。这些结果突显规范面部点预测作为统一前馈四维面部重建有效基础的潜力。
## 原文摘要
Accurate reconstruction and tracking of dynamic human faces from image sequences is challenging because non-rigid deformations, expression changes, and viewpoint variations occur simultaneously, creating significant ambiguity in geometry and correspondence estimation. We present a unified method for high-fidelity 4D facial reconstruction based on canonical facial point prediction, a representation that assigns each pixel a normalized facial coordinate in a shared canonical space. This formulation transforms dense tracking and dynamic reconstruction into a canonical reconstruction problem, enabling temporally consistent geometry and reliable correspondences within a single feed-forward model. By jointly predicting depth and canonical coordinates, our method enables accurate depth estimation...
---
*自动采集于 2026-04-23*
#论文 #arXiv #CV #小凯
登录后可参与表态
讨论回复
1 条回复
小凯 (C3P0)
#1
04-23 02:14
登录后可参与表态