面向统一动态人脸关键点检测
Towards Unified Dynamic Face Landmark Detection
- University of Toronto（多伦多大学）
- ModiFace（ModiFace公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对人脸关键点检测需为不同N点数据集独立训练模型、仅能输出固定数量关键点的局限，提出FPALP概念与统一动态FLD方法，实现单模型适配多数据集、动态输出指定数量关键点，性能优于部分现有SOTA方法。
AI中文摘要：
尽管人脸关键点检测（FLD）方法的不断进步持续推动着性能边界，但它们忽视了两个主要功能局限：(1) 针对每个“N点”基准数据集，需要独立训练不同的网络参数；(2) 在“N点”数据集上训练的模型只能可靠地输出N个关键点。在本研究中，我们首先提出了人脸部件锚定关键点位置（FPALP）的概念，其中每个关键点被视为沿人脸部件轮廓的0（起点）到1（终点）之间的递进值。无论其来源数据集如何，每个关键点都可以用FPALP格式表示，从而将所有“N点”数据集统一为单个数据集。其次，我们用基于FPALP的查询表示每个关键点，通过跨模态解码器逐步优化该查询，并基于最终表示预测其坐标。我们的方法称为统一动态FLD，体现了这两个设计选择，简化了关键点检测流程，使单个模型能够在任意数量的“N点”数据集上学习，并在运行时通过加载指定的关键点查询生成任意数量的特定关键点预测。在多个基准数据集上的大量实验表明，我们的方法在实现这些优势的同时，性能与现有最先进方法相当，且在若干案例中优于这些方法。
英文摘要：
Although advancements in face landmark detection (FLD) methods continue to push performance boundaries, they overlook two major functional limitations: (1) different network parameters need to be trained independently for each ``$N$-point'' benchmark dataset, and (2) a model trained on an ``$N$-point'' dataset reliably outputs only the $N$ landmarks. In our work, we first conceptualize Face Part-Anchored Landmark Positions (FPALPs), wherein each landmark is treated as a progression value between zero (start) and one (end) along a face part's contour. Every landmark can be expressed in the FPALP format, irrespective of its source dataset, hence unlocking the ability to unify all ``$N$-point'' datasets into a single dataset. Secondly, we represent each landmark with an FPALP-based query, refine it progressively with a cross-modality decoder, and predict its coordinates based on the final representation. Our approach, called Unified Dynamic FLD, embodies these two design choices and streamlines the landmark detection pipeline by enabling (1) a single model to learn on any number of ``$N$-point'' datasets, and (2) yield any number of specific landmark predictions by loading the designated landmark queries at runtime. Extensive experiments on multiple benchmark datasets show that our method delivers these benefits while remaining competitive with, and in several cases outperforming existing state-of-the-art methods.
