mlsanityData to 7 Oct 2026

Neural 3D Clothes Retargeting from a Single Image

arXiv 2102.00062 ↗First posted 29 Jan 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a method of clothes retargeting; generating the potential poses and deformations of a given 3D clothing template model to fit onto a person in a single RGB image. The problem is fundamentally ill-posed as attaining the ground truth data is impossible, i.e., images of people wearing the different 3D clothing template model at exact same pose. We address this challenge by utilizing large-scale synthetic data generated from physical simulation, allowing us to map 2D dense body pose to 3D clothing deformation. With the simulated data, we propose a semi-supervised learning framework that validates the physical plausibility of the 3D deformation by matching with the prescribed body-to-cloth contact points and clothing silhouette to fit onto the unlabeled real images. A new neural clothes retargeting network (CRNet) is designed to integrate the semi-supervised retargeting task in an end-to-end fashion. In our evaluation, we show that our method can predict the realistic 3D pose and deformation field needed for retargeting clothes models in real-world examples.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 30 of its 70 references that are in the map. First posted on arXiv 29 Jan 2021.

Builds on

30 of 70 references.

References · 30

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2017End-to-end Recovery of Human Shape and Posecited by 883
  3. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  4. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  5. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  6. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  7. 2017Learning from Synthetic Humanscited by 358
  8. 2017VITON: An Image-based Virtual Try-on Networkcited by 285
  9. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  10. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  11. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  12. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
18 more
  1. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 147
  2. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  3. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  4. 2018DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensorcited by 95
  5. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  6. 2017Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hzcited by 91
  7. 2018DeepWrinkles: Accurate and Realistic Clothing Modelingcited by 90
  8. 2019Learning-Based Animation of Clothing for Virtual Try-Oncited by 89
  9. 2016Learning Detailed Face Reconstruction from a Single Imagecited by 71
  10. 2018GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Drapingcited by 69
  11. 2016Synthesizing Training Images for Boosting Human 3D Pose Estimationcited by 52
  12. 2017Be Your Own Prada: Fashion Synthesis with Structural Coherencecited by 49
  13. 2016Automatic Face Reenactmentcited by 43
  14. 2019SimulCap : Single-View Human Performance Capture with Cloth Simulationcited by 41
  15. 2017Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networkscited by 32
  16. 2016Detailed Garment Recovery from a Single-View Imagecited by 16
  17. 2019Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Trackingcited by 12
  18. 20173D Semantic Trajectory Reconstruction from 3D Pixel Continuumcited by 4

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 1.

5 papers.

  1. 2021Point-Based Modeling of Human Clothingcited by 37
  2. 2021HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challengecited by 17
  3. 2022BodyMap: Learning Full-Body Dense Correspondence Mapcited by 11
  4. 2021Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industrycited by 4
  5. 2021fAshIon after fashion: A Report of AI in Fashioncited by 1