mlsanityData to 7 Oct 2026

SARS: A Novel Face and Body Shape and Appearance Aware 3D Reconstruction System extends Morphable Models

arXiv 2602.09918 ↗First posted 10 Feb 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Morphable Models (3DMMs) are a type of morphable model that takes 2D images as inputs and recreates the structure and physical appearance of 3D objects, especially human faces and bodies. 3DMM combines identity and expression blendshapes with a basic face mesh to create a detailed 3D model. The variability in the 3D Morphable models can be controlled by tuning diverse parameters. They are high-level image descriptors, such as shape, texture, illumination, and camera parameters. Previous research in 3D human reconstruction concentrated solely on global face structure or geometry, ignoring face semantic features such as age, gender, and facial landmarks characterizing facial boundaries, curves, dips, and wrinkles. In order to accommodate changes in these high-level facial characteristics, this work introduces a shape and appearance-aware 3D reconstruction system (named SARS by us), a c modular pipeline that extracts body and face information from a single image to properly rebuild the 3D model of the human full body.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 47 of its 78 references that are in the map. First posted on arXiv 10 Feb 2026.

Builds on

47 of 78 references.

References · 47

  1. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  3. 2017End-to-end Recovery of Human Shape and Posecited by 883
  4. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  5. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  6. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  7. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
  8. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 2018Learning 3D Human Dynamics from Videocited by 315
  11. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
  12. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
35 more
  1. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  2. 2021Mesh Graphormercited by 264
  3. 2017Integral Human Pose Regressioncited by 255
  4. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  5. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  6. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  7. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  8. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  9. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  10. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
  11. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  12. 2022Towards Metrical Reconstruction of Human Facescited by 165
  13. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  14. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  15. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  16. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  17. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  18. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  19. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  20. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  21. 2018Unsupervised Training for 3D Morphable Model Regressioncited by 99
  22. 2017Towards Accurate Markerless Human Shape and Pose Estimation over Timecited by 92
  23. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  24. 2020FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integrationcited by 72
  25. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  26. 20223D face reconstruction with dense landmarkscited by 70
  27. 20203D Human Mesh Regression with Dense Correspondencecited by 66
  28. 2020Monocular Real-time Full Body Capture with Inter-part Correlationscited by 53
  29. 2024GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusioncited by 36
  30. 2018ExpNet: Landmark-Free, Deep, 3D Facial Expressionscited by 29
  31. 2022Facial Geometric Detail Recovery via Implicit Representationcited by 27
  32. 2019LinesToFacePhoto: Face Photo Generation from Lines with Conditional Self-Attention Generative Adversarial Networkcited by 23
  33. 2024UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editingcited by 18
  34. 2024A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimationcited by 15
  35. 2022SHARP: Shape-Aware Reconstruction of People in Loose Clothingcited by 12

Built on by

Not cited yet.