Shape-Bayes：视觉模糊下结构化形状的贝叶斯推断

中文摘要 AI 辅助

在真实世界条件下，从像素感知结构化形状（如人脸）本质上是一项模糊任务。然而，形状推断通常被设定为预测固定空间坐标的确定性回归任务。我们发现，当视觉证据模糊或不完整时，确定性回归是脆弱的；在严重遮挡下，确定性模型会出现结构崩溃，预测出不连贯的形状或退化为通用平均值。为解决这一问题，我们引入了Shape-Bayes，一个将不确定性感知的视觉感知与贝叶斯形状推理相结合的概率框架。Shape-Bayes不强制点估计，而是动态权衡视觉证据与几何先验，以推断出结构有效的形状后验。在人脸形状回归这一具有复杂非刚性变形和严格解剖约束的严格测试平台上，Shape-Bayes包含：（1）一个基础模型，预测带噪声的地标以及蒸馏的偶然不确定性；（2）一个轻量级Transformer，将这些观测编码为PCA形状流形上的自适应先验；（3）一个可微的贝叶斯求解器，通过平衡噪声预测与先验来计算闭式后验。通过保证完整的结构完整性，Shape-Bayes在IDR上相比最先进的确定性模型实现了高达约34%的绝对改进。同时，它产生高度校准的不确定性边界，并将相对误差降低高达12.5%，在严重遮挡下建立了鲁棒2D人脸形状回归的新最先进水平。项目页面位于此https URL。

英文摘要

Perceiving structured shapes, such as human faces, from pixels is an inherently ambiguous task in real-world conditions. Yet, shape inference is largely posed as a deterministic regression task predicting fixed spatial coordinates. We find that deterministic regression is brittle when visual evidence is ambiguous or incomplete; under severe occlusions deterministic models exhibit structural collapse, predicting incoherent shapes or reverting to generic averages. To address this, we introduce Shape-Bayes, a probabilistic framework that couples uncertainty-aware visual perception with Bayesian shape reasoning. Rather than forcing point estimates, Shape-Bayes dynamically weights visual evidence against geometric priors to infer a structurally valid shape posterior. Demonstrated on human face shape regression, a rigorous testbed featuring complex non-rigid deformations and strict anatomical constraints, Shape-Bayes comprises: (1) a base model predicting noisy landmarks alongside distilled aleatoric uncertainties; (2) a lightweight Transformer encoding these observations into an adaptive prior over a PCA shape manifold; and (3) a differentiable Bayesian solver computing closed-form posteriors by balancing the noisy predictions against this prior. By guaranteeing complete structural integrity, Shape-Bayes achieves an absolute improvement of up to ~34% IDR over state-of-the-art deterministic models. Simultaneously, it yields highly calibrated uncertainty bounds and reduces relative error by up to 12.5%, establishing a new state-of-the-art for robust 2D face shape regression under severe occlusion. The project page is at https://shape-bayes.github.io.

发表机构

• BlueSkeye AI
• University of Nottingham（诺丁汉大学）

机构由 AI 辅助整理，请以论文原文为准。