# FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation

arXiv: https://arxiv.org/abs/2512.01444 · HTML: https://mlsanity.com/paper/2512.01444/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [What Do Single-view 3D Reconstruction Networks Learn?](https://mlsanity.com/paper/1905.03678/) (2019)
- [SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks](https://mlsanity.com/paper/2104.03313/) (2021)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [BodyNet: Volumetric Inference of 3D Human Body Shapes](https://mlsanity.com/paper/1804.04875/) (2018)
- [Human Gaussian Splatting: Real-time Rendering of Animatable Avatars](https://mlsanity.com/paper/2311.17113/) (2023)
- [ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering](https://mlsanity.com/paper/2312.05941/) (2023)
- [HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting](https://mlsanity.com/paper/2311.17061/) (2023)
- [Expressive Whole-Body 3D Gaussian Avatar](https://mlsanity.com/paper/2407.21686/) (2024)
- [Generalizable Human Gaussians for Sparse View Synthesis](https://mlsanity.com/paper/2407.12777/) (2024)
- [Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars](https://mlsanity.com/paper/2311.16482/) (2023)
- [Relightable and Animatable Neural Avatar from Sparse-View Video](https://mlsanity.com/paper/2308.07903/) (2023)
- [HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations](https://mlsanity.com/paper/2308.11261/) (2023)
- [LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh](https://mlsanity.com/paper/2502.09617/) (2025)
- [MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction](https://mlsanity.com/paper/2412.03103/) (2024)
- [AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos](https://mlsanity.com/paper/2408.02110/) (2024)
- [SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction](https://mlsanity.com/paper/2508.19688/) (2025)
- [SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction](https://mlsanity.com/paper/2506.12793/) (2025)

## Built on by (most cited first, 2 of 2)

- [MultiGO++: Monocular 3D Clothed Human Reconstruction via Geometry-Texture Collaboration](https://mlsanity.com/paper/2603.04993/) (2026)
- [MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery](https://mlsanity.com/paper/2605.05680/) (2026)

## Abstract (arXiv)

3D human avatar animation aims at transforming a human avatar from an arbitrary initial pose to a specified target pose using deformation algorithms. Existing approaches typically divide this task into two stages: canonical template construction and target pose deformation. However, current template construction methods demand extensive skeletal rigging and often produce artifacts for specific poses. Moreover, target pose deformation suffers from structural distortions caused by Linear Blend Skinning (LBS), which significantly undermines animation realism. To address these problems, we propose a unified learning-based framework to address both challenges in two phases. For the former phase, to overcome the inefficiencies and artifacts during template construction, we leverage a U-Net architecture that decouples texture and pose information in a feed-forward process, enabling fast generation of a human template. For the latter phase, we propose a data-driven refinement technique that enhances structural integrity. Extensive experiments show that our model delivers consistent performance across diverse poses with an optimal balance between efficiency and quality,surpassing state-of-the-art (SOTA) methods.