# FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision

arXiv: https://arxiv.org/abs/2512.15599 · HTML: https://mlsanity.com/paper/2512.15599/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 75 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 30 of 57)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](https://mlsanity.com/paper/1903.08527/) (2019)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [HeadNeRF: A Real-time NeRF-based Parametric Head Model](https://mlsanity.com/paper/2112.05637/) (2021)
- [NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads](https://mlsanity.com/paper/2305.03027/) (2023)
- [VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time](https://mlsanity.com/paper/2404.10667/) (2024)
- [VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution](https://mlsanity.com/paper/2205.03409/) (2022)
- [Instant Volumetric Head Avatars](https://mlsanity.com/paper/2211.12499/) (2022)
- [MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition](https://mlsanity.com/paper/2011.11961/) (2020)
- [Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks](https://mlsanity.com/paper/2112.01522/) (2021)
- [Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer](https://mlsanity.com/paper/2412.00733/) (2024)
- [Realistic One-shot Mesh-based Head Avatars](https://mlsanity.com/paper/2206.08343/) (2022)
- [FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding](https://mlsanity.com/paper/2312.02214/) (2023)
- [CelebV-Text: A Large-Scale Facial Text-Video Dataset](https://mlsanity.com/paper/2303.14717/) (2023)
- [Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis](https://mlsanity.com/paper/2401.08503/) (2024)
- [Generalizable and Animatable Gaussian Head Avatar](https://mlsanity.com/paper/2410.07971/) (2024)
- [Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild](https://mlsanity.com/paper/2003.03771/) (2020)

## Built on by (most cited first, 10 of 10)

- [UIKA: Fast Universal Head Avatar from Pose-Free Images](https://mlsanity.com/paper/2601.07603/) (2026)
- [One-Shot Feed-Forward 360circ Animatable Avatar via Inpainted UV-Space Gaussian Modeling](https://mlsanity.com/paper/2601.12770/) (2026)
- [Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars](https://mlsanity.com/paper/2604.14541/) (2026)
- [One-shot Compositional 3D Head Avatars with Deformable Hair](https://mlsanity.com/paper/2604.14782/) (2026)
- [Learning a Delighting Prior for Facial Appearance Capture in the Wild](https://mlsanity.com/paper/2605.05636/) (2026)
- [FacePlex: Toward Natural Full-Duplex Conversational Avatars](https://mlsanity.com/paper/2606.30145/) (2026)
- [Online Neural Space Time Memory for Dynamic Novel View Synthesis](https://mlsanity.com/paper/2607.15271/) (2026)
- [FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head](https://mlsanity.com/paper/2607.20922/) (2026)
- [Split and Drive: Dual-Axis Disentanglement for Real-Time Gaussian Head Avatars](https://mlsanity.com/paper/2607.28032/) (2026)
- [One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars](https://mlsanity.com/paper/2610.02207/) (2026)

## Abstract (arXiv)

We introduce FlexAvatar, a method for creating high-quality and complete 3D head avatars from a single image. A core challenge lies in the limited availability of multi-view data and the tendency of monocular training to yield incomplete 3D head reconstructions. We identify the root cause of this issue as the entanglement between driving signal and target viewpoint when learning from monocular videos. To address this, we propose a transformer-based 3D portrait animation model with learnable data source tokens, so-called bias sinks, which enables unified training across monocular and multi-view datasets. This design leverages the strengths of both data sources during inference: strong generalization from monocular data and full 3D completeness from multi-view supervision. Furthermore, our training procedure yields a smooth latent avatar space that facilitates identity interpolation and flexible fitting to an arbitrary number of input observations. In extensive evaluations on single-view, few-shot, and monocular avatar creation tasks, we verify the efficacy of FlexAvatar. Many existing methods struggle with view extrapolation while FlexAvatar generates complete 3D head avatars with realistic facial animations. Website: https://tobias-kirschstein.github.io/flexavatar/