提出可预测每点可见性的面部关键点检测方法，提升遮挡下鲁棒性。
OccFace: Unified Occlusion-Aware Facial Landmark Detection with Per-Point Visibility
- 统一100点密集布局，结合局部与跨点上下文联合预测坐标和可见性。
- 在遮挡和大角度旋转下，被遮区域精度提升显著，可见点精度不下降。
- 适用于真人、卡通角色等多样人脸，适合需要精确可见性信息的应用。
遮挡下的准确面部关键点检测仍具挑战，尤其针对外观差异大、因旋转产生自遮挡的人类及拟人化面孔。现有方法通常隐式处理遮挡，未输出可被下游应用利用的逐点可见性。本文提出OccFace，一种面向通用拟人化面孔（包括人类、风格化角色及其他非人类设计）的遮挡感知框架。该方法采用统一的100点密集布局与基于热图的骨干网络，并引入遮挡模块，通过融合局部证据与跨点上下文，联合预测关键点坐标与逐点可见性。可见性监督结合人工标注与基于掩码-热图重叠生成的伪可见性标签。我们还构建了包含100点关键点与逐点可见性标注的数据集，并设计评估体系，报告可见/被遮点的NME，以及用Occ AP、[email protected]和ROC-AUC衡量可见性性能。实验表明，该方法在外部遮挡与大头姿旋转下表现更鲁棒，尤其在被遮区域提升明显，同时保持可见点的高精度。
原文摘要 · Abstract (English)
Accurate facial landmark detection under occlusion remains challenging, especially for human-like faces with large appearance variation and rotation-driven self-occlusion. Existing detectors typically localize landmarks while handling occlusion implicitly, without predicting per-point visibility that downstream applications can benefits. We present OccFace, an occlusion-aware framework for universal human-like faces, including humans, stylized characters, and other non-human designs. OccFace adopts a unified dense 100-point layout and a heatmap-based backbone, and adds an occlusion module that jointly predicts landmark coordinates and per-point visibility by combining local evidence with cross-landmark context. Visibility supervision mixes manual labels with landmark-aware masking that derives pseudo visibility from mask-heatmap overlap. We also create an occlusion-aware evaluation suite reporting NME on visible vs. occluded landmarks and benchmarking visibility with Occ AP, [email protected], and ROC-AUC, together with a dataset annotated with 100-point landmarks and per-point visibility. Experiments show improved robustness under external occlusion and large head rotations, especially on occluded regions, while preserving accuracy on visible landmarks.
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。