# MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning

arXiv: https://arxiv.org/abs/2502.02372 · HTML: https://mlsanity.com/paper/2502.02372/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 4 Feb 2025.

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

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [NeuMan: Neural Human Radiance Field from a Single Video](https://mlsanity.com/paper/2203.12575/) (2022)
- [GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians](https://mlsanity.com/paper/2312.02134/) (2023)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs](https://mlsanity.com/paper/2112.02789/) (2021)
- [Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes](https://mlsanity.com/paper/2304.03266/) (2023)
- [HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting](https://mlsanity.com/paper/2311.17061/) (2023)
- [SHERF: Generalizable Human NeRF from a Single Image](https://mlsanity.com/paper/2303.12791/) (2023)
- [MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images](https://mlsanity.com/paper/2203.16875/) (2022)
- [Text-Guided Generation and Editing of Compositional 3D Avatars](https://mlsanity.com/paper/2309.07125/) (2023)
- [S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation](https://mlsanity.com/paper/2402.02112/) (2024)
- [Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor](https://mlsanity.com/paper/2204.13349/) (2022)
- [UC-NeRF: Neural Radiance Field for Under-Calibrated Multi-view Cameras in Autonomous Driving](https://mlsanity.com/paper/2311.16945/) (2023)
- [ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs](https://mlsanity.com/paper/2304.14401/) (2023)
- [Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling](https://mlsanity.com/paper/2304.04897/) (2023)
- [TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering](https://mlsanity.com/paper/2307.12291/) (2023)
- [Human 3D Avatar Modeling with Implicit Neural Representation: A Brief Survey](https://mlsanity.com/paper/2306.03576/) (2023)
- [IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment](https://mlsanity.com/paper/2312.05748/) (2023)
- [PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments](https://mlsanity.com/paper/2402.09325/) (2024)

## Abstract (arXiv)

The generation of a virtual digital avatar is a crucial research topic in the field of computer vision. Many existing works utilize Neural Radiance Fields (NeRF) to address this issue and have achieved impressive results. However, previous works assume the images of the training person are available and fixed while the appearances and poses of a subject could constantly change and increase in real-world scenarios. How to update the human avatar but also maintain the ability to render the old appearance of the person is a practical challenge. One trivial solution is to combine the existing virtual avatar models based on NeRF with continual learning methods. However, there are some critical issues in this approach: learning new appearances and poses can cause the model to forget past information, which in turn leads to a degradation in the rendering quality of past appearances, especially color bleeding issues, and incorrect human body poses. In this work, we propose a maintainable avatar (MaintaAvatar) based on neural radiance fields by continual learning, which resolves the issues by utilizing a Global-Local Joint Storage Module and a Pose Distillation Module. Overall, our model requires only limited data collection to quickly fine-tune the model while avoiding catastrophic forgetting, thus achieving a maintainable virtual avatar. The experimental results validate the effectiveness of our MaintaAvatar model.