Back to search

Article

Recovering 3D Facial Geometry from 2D Images: Mathematical Foundations and Comprehensive Benchmarking

2026-03-02

Abstract excerpt

Standard RGB cameras measure radiance on an image plane but discard the scene depth that governs the three-dimensional (3D) geometry of the human face. Recovering facial depth from one or more 2D images is ill-posed: infinitely many 3D shapes can explain the same pixels under unknown illumination, pose, and occlusion. This paper develops a unified, math-forward narrative of the field under the central thesis of ge...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
3d2f03f7-9456-5355-a6bb-c9ba6d381c50
DOI
10.22541/au.177247326.69299749/v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Recovering 3D Facial Geometry from 2D Images: Mathematical Foundations and Comprehensive BenchmarkingDOI 10.22541/au.177247326.69299749/v1
UniFacePoint-FM: A Foundation Model for Generalizable 3D Facial Representation Learning and Multi-Attribute PredictionSemantic proximity
Face dissimilarity judgements are predicted by representational distance in morphable and image-computable modelsSemantic proximity
Mono-Splat: Real-Time Photorealistic Human Avatar Reconstruction from Monocular Webcam Video via Deformable 3D Gaussian SplattingSemantic proximity
Efficient task generalization and humanlike face perception in models that learn to discriminate face geometrySemantic proximity
A Hybrid Neural Framework for Robust Image Analysis under Data and Sensor ConstraintsSemantic proximity
Enabling Safe UAV Navigation in Transparent and Specular Environments via Generative Depth CompletionSemantic proximity
Action Unit-Based 3D Face Reconstruction Using TransformersSemantic proximity
Action Unit-Based 3D Face Reconstruction Using TransformersSemantic proximity
Action Unit-Based 3D Face Reconstruction Using TransformersSemantic proximity
Realtime Glasses-Free 3D Display with Seamless Ultrawide Viewing Range using Deep LearningSemantic proximity
Ultraman: Ultra-Fast and High-Resolution Texture Generation for 3D Human Reconstruction from a Single ImageSemantic proximity
A deep convolutional neural network trained for lightness constancy is susceptible to lightness illusionsSemantic proximity
Select a neighboring publication to make it the new centre.