# Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition

arXiv: https://arxiv.org/abs/2302.11566 · HTML: https://mlsanity.com/paper/2302.11566/

## Key facts

- Cited by 134 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 80 references that are in the map.
- First posted on arXiv 22 Feb 2023.

## Builds on (most cited first, 30 of 56)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](https://mlsanity.com/paper/2105.02872/) (2021)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [ARCH: Animatable Reconstruction of Clothed Humans](https://mlsanity.com/paper/2004.04572/) (2020)
- [NeuMan: Neural Human Radiance Field from a Single Video](https://mlsanity.com/paper/2203.12575/) (2022)
- [Video Based Reconstruction of 3D People Models](https://mlsanity.com/paper/1803.04758/) (2018)
- [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](https://mlsanity.com/paper/2102.06199/) (2021)
- [PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction](https://mlsanity.com/paper/2007.03858/) (2020)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Monocular, One-stage, Regression of Multiple 3D People](https://mlsanity.com/paper/2008.12272/) (2020)
- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)
- [ARCH++: Animation-Ready Clothed Human Reconstruction Revisited](https://mlsanity.com/paper/2108.07845/) (2021)
- [Neural Volumes: Learning Dynamic Renderable Volumes from Images](https://mlsanity.com/paper/1906.07751/) (2019)
- [TAVA: Template-free Animatable Volumetric Actors](https://mlsanity.com/paper/2206.08929/) (2022)
- [DeepCap: Monocular Human Performance Capture Using Weak Supervision](https://mlsanity.com/paper/2003.08325/) (2020)
- [H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion](https://mlsanity.com/paper/2110.13746/) (2021)
- [Editable Free-viewpoint Video Using a Layered Neural Representation](https://mlsanity.com/paper/2104.14786/) (2021)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)

## Built on by (most cited first, 30 of 134)

- [3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2312.09228/) (2023)
- [GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians](https://mlsanity.com/paper/2312.02134/) (2023)
- [SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting](https://mlsanity.com/paper/2403.05087/) (2024)
- [GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis](https://mlsanity.com/paper/2312.02155/) (2023)
- [HUGS: Human Gaussian Splats](https://mlsanity.com/paper/2311.17910/) (2023)
- [GART: Gaussian Articulated Template Models](https://mlsanity.com/paper/2311.16099/) (2023)
- [EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild](https://mlsanity.com/paper/2308.16894/) (2023)
- [Expressive Whole-Body 3D Gaussian Avatar](https://mlsanity.com/paper/2407.21686/) (2024)
- [Hi4D: 4D Instance Segmentation of Close Human Interaction](https://mlsanity.com/paper/2303.15380/) (2023)
- [HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video](https://mlsanity.com/paper/2311.18448/) (2023)
- [SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction](https://mlsanity.com/paper/2312.06704/) (2023)
- [SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion](https://mlsanity.com/paper/2311.15855/) (2023)
- [X-Avatar: Expressive Human Avatars](https://mlsanity.com/paper/2303.04805/) (2023)
- [MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling](https://mlsanity.com/paper/2409.16160/) (2024)
- [Learning Locally Editable Virtual Humans](https://mlsanity.com/paper/2305.00121/) (2023)
- [4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations](https://mlsanity.com/paper/2404.18630/) (2024)
- [REACTO: Reconstructing Articulated Objects from a Single Video](https://mlsanity.com/paper/2404.11151/) (2024)
- [GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splatting](https://mlsanity.com/paper/2401.09720/) (2024)
- [MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos](https://mlsanity.com/paper/2407.08414/) (2024)
- [Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior](https://mlsanity.com/paper/2503.01610/) (2025)
- [Animatable and Relightable Gaussians for High-fidelity Human Avatar Modeling](https://mlsanity.com/paper/2311.16096/) (2023)
- [Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos](https://mlsanity.com/paper/2403.17103/) (2024)
- [AI-Generated Content (AIGC) for Various Data Modalities: A Survey](https://mlsanity.com/paper/2308.14177/) (2023)
- [LayGA: Layered Gaussian Avatars for Animatable Clothing Transfer](https://mlsanity.com/paper/2405.07319/) (2024)
- [GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views](https://mlsanity.com/paper/2411.11363/) (2024)
- [IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing](https://mlsanity.com/paper/2312.05210/) (2023)
- [ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild](https://mlsanity.com/paper/2409.15269/) (2024)
- [Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses](https://mlsanity.com/paper/2404.14410/) (2024)
- [iHuman: Instant Animatable Digital Humans From Monocular Videos](https://mlsanity.com/paper/2407.11174/) (2024)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)

## Abstract (arXiv)

We present Vid2Avatar, a method to learn human avatars from monocular in-the-wild videos. Reconstructing humans that move naturally from monocular in-the-wild videos is difficult. Solving it requires accurately separating humans from arbitrary backgrounds. Moreover, it requires reconstructing detailed 3D surface from short video sequences, making it even more challenging. Despite these challenges, our method does not require any groundtruth supervision or priors extracted from large datasets of clothed human scans, nor do we rely on any external segmentation modules. Instead, it solves the tasks of scene decomposition and surface reconstruction directly in 3D by modeling both the human and the background in the scene jointly, parameterized via two separate neural fields. Specifically, we define a temporally consistent human representation in canonical space and formulate a global optimization over the background model, the canonical human shape and texture, and per-frame human pose parameters. A coarse-to-fine sampling strategy for volume rendering and novel objectives are introduced for a clean separation of dynamic human and static background, yielding detailed and robust 3D human geometry reconstructions. We evaluate our methods on publicly available datasets and show improvements over prior art.