Shape-Bayes: Bayesian Inference of Structured Shapes under Visual Ambiguity
Quick Answer
Shape-Bayes introduces a probabilistic framework for inferring structured shapes like human faces under visual ambiguity, outperforming deterministic models by up to 34% in IDR.
Quick Take
It combines uncertainty-aware perception with Bayesian reasoning, achieving reduced relative error by 12.5% and ensuring structural integrity during severe occlusions.
Key Points
- Shape-Bayes dynamically weights visual evidence against geometric priors for shape inference.
- Achieves up to 34% improvement in IDR over state-of-the-art deterministic models.
- Reduces relative error by 12.5% while maintaining structural integrity.
- Utilizes a lightweight Transformer for adaptive prior over PCA shape manifold.
- Demonstrated effectiveness on complex human face shape regression tasks.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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 this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.09032 [cs.CV] |
| (or arXiv:2610.09032v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09032 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mani Kumar Tellamekala [view email]
[v1]
Tue, 6 Oct 2026 19:31:42 UTC (19,870 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.