mlsanityData to 7 Oct 2026

JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction

arXiv 2204.10549 ↗First posted 22 Apr 2022cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

This paper addresses the problem of single view 3D human reconstruction. Recent implicit function based methods have shown impressive results, but they fail to recover fine face details in their reconstructions. This largely degrades user experience in applications like 3D telepresence. In this paper, we focus on improving the quality of face in the reconstruction and propose a novel Jointly-aligned Implicit Face Function (JIFF) that combines the merits of the implicit function based approach and model based approach. We employ a 3D morphable face model as our shape prior and compute space-aligned 3D features that capture detailed face geometry information. Such space-aligned 3D features are combined with pixel-aligned 2D features to jointly predict an implicit face function for high quality face reconstruction. We further extend our pipeline and introduce a coarse-to-fine architecture to predict high quality texture for our detailed face model. Extensive evaluations have been carried out on public datasets and our proposed JIFF has demonstrates superior performance (both quantitatively and qualitatively) over existing state-of-the-arts.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 54 of its 78 references that are in the map. First posted on arXiv 22 Apr 2022.

Builds on

54 of 78 references.

References · 54

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  5. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  6. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2016An overview of gradient descent optimization algorithmscited by 1,021
  9. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  10. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  11. 2017End-to-end Recovery of Human Shape and Posecited by 883
  12. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
38 more
  1. 2020Convolutional Occupancy Networkscited by 760
  2. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  3. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  4. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 481
  5. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  6. 20193D Morphable Face Models -- Past, Present and Futurecited by 269
  7. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  8. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  9. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 244
  10. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  11. 2018Video Based Reconstruction of 3D People Modelscited by 237
  12. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  13. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  14. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  15. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  16. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  17. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  18. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  19. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  20. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  21. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  22. 2019NASA: Neural Articulated Shape Approximationcited by 149
  23. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 147
  24. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  25. 2020BCNet: Learning Body and Cloth Shape from A Single Imagecited by 118
  26. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  27. 2020i3DMM: Deep Implicit 3D Morphable Model of Human Headscited by 109
  28. 2020Learning Human-Object Interaction Detection using Interaction Pointscited by 108
  29. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  30. 2017Detailed, accurate, human shape estimation from clothed 3D scan sequencescited by 89
  31. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  32. 2020Monocular Real-Time Volumetric Performance Capturecited by 74
  33. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  34. 2018SiCloPe: Silhouette-Based Clothed Peoplecited by 68
  35. 2021DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Camerascited by 67
  36. 2019Towards a complete 3D morphable model of the human headcited by 63
  37. 2020Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networkscited by 51
  38. 2019Combining 3D Morphable Models: A Large scale Face-and-Head Modelcited by 49

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 15; 2024: 5; 2025: 3; 2026: 1.

26 papers.

Sort:

By area:

  1. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  2. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  3. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  4. 2025LHM: Large Animatable Human Reconstruction Model from a Single Image in Secondscited by 61
  5. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  6. 2024AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstructioncited by 36
  7. 2023SplatArmor: Articulated Gaussian splatting for animatable humans from monocular RGB videoscited by 35
  8. 2023REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videoscited by 29
  9. 2022Structured 3D Features for Reconstructing Controllable Avatarscited by 19
  10. 2023Single-Shot Implicit Morphable Faces with Consistent Texture Parameterizationcited by 16
  11. 2023SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstructioncited by 15
  12. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
14 more
  1. 2023Guide3D: Create 3D Avatars from Text and Image Guidancecited by 10
  2. 2023Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstructioncited by 8
  3. 2023LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstructioncited by 6
  4. 2025LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3Dcited by 6
  5. 2023High-Quality Animatable Dynamic Garment Reconstruction from Monocular Videoscited by 5
  6. 2023Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fieldscited by 5
  7. 2022Occupancy Planes for Single-view RGB-D Human Reconstructioncited by 4
  8. 2023SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpaintingcited by 3
  9. 2023Refining 3D Human Texture Estimation from a Single Imagecited by 2
  10. 2023Mesh Strikes Back: Fast and Efficient Human Reconstruction from RGB videoscited by 2
  11. 2024FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesiscited by 1
  12. 2024Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUscited by 0
  13. 2025GLVD: Guided Learned Vertex Descentcited by 0
  14. 2026ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Losscited by 0