mlsanityData to 14 Oct 2026

FIELDS: Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision

arXiv 2511.21245 ↗First posted 26 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Monocular 3D face reconstruction estimates a 3D morphable model (3DMM) representation from a single image, providing geometry-aware expression codes that are useful for facial expression analysis and affect understanding. Despite strong progress, most pipelines are trained with image-level self-supervision and evaluated primarily by geometric fidelity, which does not necessarily maximize the affective utility of the learned expression representation and may encourage intensity-amplifying shortcuts when affect supervision is naively coupled. We propose FIELDS (Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision), a task-driven framework that learns FLAME expression codes for facial expression recognition (FER) under a geometric plausibility constraint. Using hybrid 2D/3D supervision, FIELDS improves affect prediction in both in-domain and external evaluations while maintaining competitive geometric fidelity on held-out and out-of-domain 3D benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 74 references that are in the map. First posted on arXiv 26 Nov 2025.

Builds on

38 of 74 references.

References · 38

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
  8. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 525
  9. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  10. 2017AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wildcited by 492
  11. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 482
  12. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
26 more
  1. 2018Deep Facial Expression Recognition: A Surveycited by 270
  2. 20193D Morphable Face Models -- Past, Present and Futurecited by 270
  3. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 255
  4. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  5. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
  6. 2019Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervisioncited by 176
  7. 2022Towards Metrical Reconstruction of Human Facescited by 166
  8. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  9. 2017Morphable Face Models - An Open Frameworkcited by 138
  10. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  11. 2018Unsupervised Training for 3D Morphable Model Regressioncited by 100
  12. 2022Multiface: A Dataset for Neural Face Renderingcited by 87
  13. 2024SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesiscited by 84
  14. 2020Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistencycited by 78
  15. 20223D face reconstruction with dense landmarkscited by 70
  16. 2019Towards a complete 3D morphable model of the human headcited by 63
  17. 2019MVF-Net: Multi-View 3D Face Morphable Model Regressioncited by 45
  18. 2018DenseReg: Fully Convolutional Dense Shape Regression In-the-Wildcited by 32
  19. 2018ExpNet: Landmark-Free, Deep, 3D Facial Expressionscited by 29
  20. 2017Dense Face Alignmentcited by 24
  21. 2024A Survey on Facial Expression Recognition of Static and Dynamic Emotionscited by 15
  22. 2025TEASER: Token Enhanced Spatial Modeling for Expressions Reconstructioncited by 14
  23. 2020Real-time Facial Expression Recognition "In The Wild'' by Disentangling 3D Expression from Identitycited by 8
  24. 2024Ig3D: Integrating 3D Face Representations in Facial Expression Inferencecited by 6
  25. 2022Are 3D Face Shapes Expressive Enough for Recognising Continuous Emotions and Action Unit Intensities?cited by 4
  26. 2024SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargetingcited by 4

Built on by

Not cited yet.