# GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion

arXiv: https://arxiv.org/abs/2412.10209 · HTML: https://mlsanity.com/paper/2412.10209/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 96 of its 113 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 96)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)

## Built on by (most cited first, 30 of 36)

- [Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2502.20220/) (2025)
- [Monocular and Generalizable Gaussian Talking Head Animation](https://mlsanity.com/paper/2504.00665/) (2025)
- [UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections](https://mlsanity.com/paper/2509.24817/) (2025)
- [SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians](https://mlsanity.com/paper/2504.12292/) (2025)
- [DyTact: Capturing Dynamic Contacts in Hand-Object Manipulation](https://mlsanity.com/paper/2506.03103/) (2025)
- [MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics](https://mlsanity.com/paper/2510.01619/) (2025)
- [CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis](https://mlsanity.com/paper/2505.17590/) (2025)
- [Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priors](https://mlsanity.com/paper/2508.08384/) (2025)
- [MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis](https://mlsanity.com/paper/2510.07190/) (2025)
- [STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction](https://mlsanity.com/paper/2511.19854/) (2025)
- [FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation](https://mlsanity.com/paper/2601.13837/) (2026)
- [Controlling Avatar Diffusion with Learnable Gaussian Embedding](https://mlsanity.com/paper/2503.15809/) (2025)
- [HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars](https://mlsanity.com/paper/2507.02803/) (2025)
- [Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding](https://mlsanity.com/paper/2512.04313/) (2025)
- [AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars](https://mlsanity.com/paper/2512.06438/) (2025)
- [FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation](https://mlsanity.com/paper/2512.17717/) (2025)
- [ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatars](https://mlsanity.com/paper/2510.05488/) (2025)
- [FactorPortrait: Controllable Portrait Animation via Disentangled Expression, Pose, and Viewpoint](https://mlsanity.com/paper/2512.11645/) (2025)
- [ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptation](https://mlsanity.com/paper/2601.10200/) (2026)
- [OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar](https://mlsanity.com/paper/2603.01506/) (2026)
- [AvatarPointillist: AutoRegressive 4D Gaussian Avatarization](https://mlsanity.com/paper/2604.04787/) (2026)
- [Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures](https://mlsanity.com/paper/2605.04035/) (2026)
- [Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation](https://mlsanity.com/paper/2605.25220/) (2026)
- [EgoAnimate: Generating Human Animations from Egocentric top-down Views](https://mlsanity.com/paper/2507.09230/) (2025)
- [GLVD: Guided Learned Vertex Descent](https://mlsanity.com/paper/2510.06046/) (2025)
- [Instant Expressive Gaussian Head Avatars at Over 100 FPS](https://mlsanity.com/paper/2512.16893/) (2025)
- [SARS: A Novel Face and Body Shape and Appearance Aware 3D Reconstruction System extends Morphable Models](https://mlsanity.com/paper/2602.09918/) (2026)
- [FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures](https://mlsanity.com/paper/2603.23345/) (2026)
- [EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion](https://mlsanity.com/paper/2604.05794/) (2026)
- [Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars](https://mlsanity.com/paper/2606.05912/) (2026)

## Abstract (arXiv)

We propose a novel approach for reconstructing animatable 3D Gaussian avatars from monocular videos captured by commodity devices like smartphones. Photorealistic 3D head avatar reconstruction from such recordings is challenging due to limited observations, which leaves unobserved regions under-constrained and can lead to artifacts in novel views. To address this problem, we introduce a multi-view head diffusion model, leveraging its priors to fill in missing regions and ensure view consistency in Gaussian splatting renderings. To enable precise viewpoint control, we use normal maps rendered from FLAME-based head reconstruction, which provides pixel-aligned inductive biases. We also condition the diffusion model on VAE features extracted from the input image to preserve facial identity and appearance details. For Gaussian avatar reconstruction, we distill multi-view diffusion priors by using iteratively denoised images as pseudo-ground truths, effectively mitigating over-saturation issues. To further improve photorealism, we apply latent upsampling priors to refine the denoised latent before decoding it into an image. We evaluate our method on the NeRSemble dataset, showing that GAF outperforms previous state-of-the-art methods in novel view synthesis. Furthermore, we demonstrate higher-fidelity avatar reconstructions from monocular videos captured on commodity devices.