# AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging arXiv: https://arxiv.org/abs/2211.07818 ยท HTML: https://mlsanity.com/paper/2211.07818/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 35 of its 62 references that are in the map. - First posted on arXiv 15 Nov 2022. ## Builds on (most cited first, 30 of 35) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018) - [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018) - [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016) - [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014) - [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019) - [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016) - [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013) - [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020) - [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018) - [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018) - [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020) - [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019) - [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021) - [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](https://mlsanity.com/paper/1903.08527/) (2019) - [3D Morphable Face Models -- Past, Present and Future](https://mlsanity.com/paper/1909.01815/) (2019) - [FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction](https://mlsanity.com/paper/2003.13989/) (2020) - [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021) - [Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains](https://mlsanity.com/paper/2010.05334/) (2020) - [Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks](https://mlsanity.com/paper/2110.08398/) (2021) - [Deep 3D Portrait from a Single Image](https://mlsanity.com/paper/2004.11598/) (2020) - [Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement](https://mlsanity.com/paper/2106.11423/) (2021) - [Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space](https://mlsanity.com/paper/2009.06529/) (2020) - [Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation](https://mlsanity.com/paper/2008.07132/) (2020) - [DeepSketch2Face: A Deep Learning Based Sketching System for 3D Face and Caricature Modeling](https://mlsanity.com/paper/1706.02042/) (2017) - [MeInGame: Create a Game Character Face from a Single Portrait](https://mlsanity.com/paper/2102.02371/) (2021) - [3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction](https://mlsanity.com/paper/2103.08204/) (2021) - [Alive Caricature from 2D to 3D](https://mlsanity.com/paper/1803.06802/) (2018) - [Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model](https://mlsanity.com/paper/2004.09190/) (2020) ## Built on by (most cited first, 10 of 10) - [AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control](https://mlsanity.com/paper/2303.17606/) (2023) - [AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning](https://mlsanity.com/paper/2303.14297/) (2023) - [SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines](https://mlsanity.com/paper/2301.08153/) (2023) - [Tag-based annotation creates better avatars](https://mlsanity.com/paper/2302.07354/) (2023) - [Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars](https://mlsanity.com/paper/2503.11978/) (2025) - [T2Bs: Text-to-Character Blendshapes via Video Generation](https://mlsanity.com/paper/2509.10678/) (2025) - [Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning](https://mlsanity.com/paper/2310.04194/) (2023) - [Biometrics in Extended Reality: A Review](https://mlsanity.com/paper/2411.10489/) (2024) - [EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting](https://mlsanity.com/paper/2503.01158/) (2025) - [RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration](https://mlsanity.com/paper/2607.12206/) (2026) ## Abstract (arXiv) Stylized 3D avatars have become increasingly prominent in our modern life. Creating these avatars manually usually involves laborious selection and adjustment of continuous and discrete parameters and is time-consuming for average users. Self-supervised approaches to automatically create 3D avatars from user selfies promise high quality with little annotation cost but fall short in application to stylized avatars due to a large style domain gap. We propose a novel self-supervised learning framework to create high-quality stylized 3D avatars with a mix of continuous and discrete parameters. Our cascaded domain bridging framework first leverages a modified portrait stylization approach to translate input selfies into stylized avatar renderings as the targets for desired 3D avatars. Next, we find the best parameters of the avatars to match the stylized avatar renderings through a differentiable imitator we train to mimic the avatar graphics engine. To ensure we can effectively optimize the discrete parameters, we adopt a cascaded relaxation-and-search pipeline. We use a human preference study to evaluate how well our method preserves user identity compared to previous work as well as manual creation. Our results achieve much higher preference scores than previous work and close to those of manual creation. We also provide an ablation study to justify the design choices in our pipeline.