Unsupervised Creation of Parameterized Avatars

We study the problem of mapping an input image to a tied pair consisting of a vector of parameters and an image that is created using a graphical engine from the vector of parameters. The mapping's objective is to have the output image as similar as possible to the input image. During training, no supervision is given in the form of matching inputs and outputs. This learning problem extends two literature problems: unsupervised domain adaptation and cross domain transfer. We define a generalization bound that is based on discrepancy, and employ a GAN to implement a network solution that corresponds to this bound. Experimentally, our method is shown to solve the problem of automatically creating avatars.

• Publication year

  2017

• Venue

  IEEE International Conference on Computer Vision

• Publication date

  2017-04-19

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICCV.2017.170arXiv 1704.05693
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Theory of Output-Side Unsupervised Domain Adaptation

  2017cited by this paper
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution

  2016cited by this paper
• Generative Adversarial Text to Image Synthesis

  2016cited by this paper
• Unsupervised Cross-Domain Image Generation

  2016influential reference
• Unsupervised Learning of 3D Structure from Images

  2016cited by this paper
• Fast Face Sketch Synthesis via KD-Tree Search

  2016cited by this paper
• Image-to-Image Translation with Conditional Adversarial Networks

  2016cited by this paper
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images

  2016cited by this paper
• Generating Images with Perceptual Similarity Metrics based on Deep Networks

  2016cited by this paper
• Coupled Generative Adversarial Networks

  2016cited by this paper
• Image Style Transfer Using Convolutional Neural Networks

  2016cited by this paper
• DRAW: A Recurrent Neural Network For Image Generation

  2015cited by this paper
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

  2015cited by this paper
• From Facial Parts Responses to Face Detection: A Deep Learning Approach

  2015cited by this paper
• Domain-Adversarial Training of Neural Networks

  2015influential reference
• Deep Face Recognition

  2015cited by this paper
• Deep Convolutional Inverse Graphics Network

  2015cited by this paper
• Deep Learning Face Attributes in the Wild

  2014cited by this paper
• DeepFace: Closing the Gap to Human-Level Performance in Face Verification

  2014cited by this paper
• Conditional Generative Adversarial Nets

  2014cited by this paper
• A data-driven approach to cleaning large face datasets

  2014cited by this paper
• Learning to generate chairs with convolutional neural networks

  2014cited by this paper
• Network In Network

  2013cited by this paper
• Transductive Face Sketch-Photo Synthesis

  2013cited by this paper
• A theory of learning from different domains

  2010cited by this paper
• Domain Adaptation: Learning Bounds and Algorithms

  2009cited by this paper
• Learning from Multiple Sources

  2006cited by this paper
• Simple statistical gradient-following algorithms for connectionist reinforcement learning

  1992cited by this paper

• Virtual agents as a scalable tool for diverse, robust gesture recognition

  2026cites this paper
• A Segmentation-Independent Workflow for Digital Rock Property Prediction Using Pore-Structure-Preserving Generative Adversarial Networks and Synthetic Data: Porosity Case Study

  2025cites this paper
• Spiritus: An AI-Assisted Tool for Creating 2D Characters and Animations

  2025cites this paper
• Text2AC: A Framework for Game-Ready 2D Agent Character(AC) Generation from Natural Language

  2024cites this paper
• Animated Avatar Generation Technology Research Based on Deep Convolutional Generative Adversarial Network Integrated With Self-Attention and Spectral Normalization

  2024cites this paper
• Biometrics in extended reality: a review

  2024cites this paper
• Unsupervised Cross-Domain Regression for Fine-grained 3D Game Character Reconstruction

  2024cites this paper
• Bring Your Own Character: A Holistic Solution for Automatic Facial Animation Generation of Customized Characters

  2024cites this paper
• ICE: Interactive 3D Game Character Editing via Dialogue

  2024cites this paper
• Cross-modal Latent Space Alignment for Image to Avatar Translation

  2023cites this paper
• Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation

  2023cites this paper
• SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines

  2023cites this paper
• Real‐time Virtual‐Try‐On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers

  2022cites this paper
• Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet Style

  2022cites this paper
• Discriminative shared transform learning for sketch to image matching

  2021cites this paper
• An Adversarial Variational Autoencoder Approach Toward Transfer Learning for mTBI Identification

  2021cites this paper
• Inspirational Adversarial Image Generation

  2021cites this paper
• A Hybrid Deep Learning Architecture for the Classification of Superhero Fashion Products: An Application for Medical-Tech Classification

  2020cites this paper
• Particularity Beyond Commonality: Unpaired Identity Transfer with Multiple References

  2020cites this paper
• Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation

  2020cites this paper
• Advances in deep learning with limited supervision and computational resources

  2020cites this paper
• Neural Rendering for Game Character Auto-Creation

  2020cites this paper
• Neutral Face Game Character Auto-Creation via PokerFace-GAN

  2020cites this paper
• Unsupervised Generation of Free-Form and Parameterized Avatars

  2020cites this paper
• Unsupervised generation of artistic representations

  2020cites this paper
• Uncouple Generative Adversarial Networks for Transferring Stylized Portraits to Realistic Faces

  2020cites this paper
• Leveraging structure in Computer Vision tasks for flexible Deep Learning models

  2020cites this paper
• Co-Generation with GANs using AIS based HMC

  2019cites this paper
• Attribute-Guided Sketch Generation

  2019cites this paper
• GANSynth: Adversarial Neural Audio Synthesis

  2019cites this paper
• Learning representations of speech from the raw waveform. (Apprentissage de représentations de la parole à partir du signal brut)

  2019cites this paper
• Feature visualization in comic artist classification using deep neural networks

  2019cites this paper
• Attribute-Driven Spontaneous Motion in Unpaired Image Translation

  2019cites this paper
• Landmark Assisted CycleGAN for Cartoon Face Generation

  2019influential citation
• R e g r esso r Global Discriminators Landmark Consistency Conditional Eyes LocalUnconditional Local Discriminators Nose Local Mouth

  2019cites this paper
• BeautyGlow: On-Demand Makeup Transfer Framework With Reversible Generative Network

  2019cites this paper
• Unsupervised Facial Image Synthesis Using Two-Discriminator Adversarial Autoencoder Network

  2019cites this paper
• Exaggerated Portrait Caricatures Generation Based On Seq2Seq

  2019cites this paper
• Image-to-Image Translation with GAN for Synthetic Data Augmentation in Plant Disease Datasets

  2019cites this paper
• Face-to-Parameter Translation for Game Character Auto-Creation

  2019cites this paper
• Deep Learning for Classical Japanese Literature

  2018cites this paper
• NAM - UNSUPERVISED CROSS-DOMAIN IMAGE MAP-

  2018cites this paper
• NAM: Non-Adversarial Unsupervised Domain Mapping

  2018cites this paper
• Multimodal Unsupervised Image-to-Image Translation

  2018cites this paper
• Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model

  2018cites this paper
• Improving Shape Deformation in Unsupervised Image-to-Image Translation

  2018cites this paper
• Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

  2018cites this paper
• XGAN: Unsupervised Image-to-Image Translation for many-to-many Mappings

  2017influential citation
• Estimating the Success of Unsupervised Image to Image Translation

  2017cites this paper
• Dynamics Transfer GAN: Generating Video by Transferring Arbitrary Temporal Dynamics from a Source Video to a Single Target Image

  2017cites this paper
• Maximally Distant Cross Domain Generators for Estimating Per-Sample Error

  2017cites this paper
• Adversarial Information Factorization

  2017cites this paper
• High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks

  2017cites this paper
• Conditional Autoencoders with Adversarial Information Factorization

  2017cites this paper
• f-GANs in an Information Geometric Nutshell

  2017cites this paper
• Fader Networks: Manipulating Images by Sliding Attributes

  2017cites this paper