# High-Fidelity Mobile Avatars with Pruned Local Blendshapes

arXiv: https://arxiv.org/abs/2605.01854 · HTML: https://mlsanity.com/paper/2605.01854/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 87 references that are in the map.
- First posted on arXiv 3 May 2026.

## Builds on (most cited first, 30 of 65)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](https://mlsanity.com/paper/2105.02872/) (2021)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [NeuMan: Neural Human Radiance Field from a Single Video](https://mlsanity.com/paper/2203.12575/) (2022)
- [Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis](https://mlsanity.com/paper/2401.02436/) (2023)
- [GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians](https://mlsanity.com/paper/2312.02134/) (2023)
- [TAVA: Template-free Animatable Volumetric Actors](https://mlsanity.com/paper/2206.08929/) (2022)
- [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)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion](https://mlsanity.com/paper/2305.06356/) (2023)
- [HUGS: Human Gaussian Splats](https://mlsanity.com/paper/2311.17910/) (2023)
- [ARAH: Animatable Volume Rendering of Articulated Human SDFs](https://mlsanity.com/paper/2210.10036/) (2022)
- [InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds](https://mlsanity.com/paper/2212.10550/) (2022)
- [Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition](https://mlsanity.com/paper/2302.11566/) (2023)
- [Real-time Deep Dynamic Characters](https://mlsanity.com/paper/2105.01794/) (2021)
- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [Pixel Codec Avatars](https://mlsanity.com/paper/2104.04638/) (2021)
- [Relightable Gaussian Codec Avatars](https://mlsanity.com/paper/2312.03704/) (2023)
- [GART: Gaussian Articulated Template Models](https://mlsanity.com/paper/2311.16099/) (2023)
- [Structured Local Radiance Fields for Human Avatar Modeling](https://mlsanity.com/paper/2203.14478/) (2022)
- [LiveCap: Real-time Human Performance Capture from Monocular Video](https://mlsanity.com/paper/1810.02648/) (2018)
- [4K4D: Real-Time 4D View Synthesis at 4K Resolution](https://mlsanity.com/paper/2310.11448/) (2023)
- [Expressive Whole-Body 3D Gaussian Avatar](https://mlsanity.com/paper/2407.21686/) (2024)
- [MonoHuman: Animatable Human Neural Field from Monocular Video](https://mlsanity.com/paper/2304.02001/) (2023)

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

- [From Splats to Silicon: Rethinking Computational Efficiency of 3DGS](https://mlsanity.com/paper/2609.06157/) (2026)
- [One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars](https://mlsanity.com/paper/2610.02207/) (2026)

## Abstract (arXiv)

We propose a method to reconstruct high-fidelity human avatars from multi-view video that can run on mobile devices. Many works can model high-quality Gaussian-based full-body avatars from multi-view video. However, these methods require heavy computation to obtain pose-dependent appearance, making deployment on mobile devices very difficult. Recent methods distill from pretrained models and model pose-dependent nonlinear Gaussian attributes by linearly combining global pose features with blendshapes. Although they can run on mobile devices, they suffer some loss of detail. We observe that nearby Gaussians are often highly correlated within a local region of the body, and can be linearly modeled with less error. Therefore, we use local linear blendshapes in small body parts to capture global nonlinear changes of Gaussian attributes. To further reduce computation and model size, we propose to remove blendshapes for Gaussians whose attributes change little, yielding a minimal blendshape representation. Our method is an end-to-end training method without a pretrained model. To make it run on multiple devices, we implement our method using WebGPU. Experiments show that our method can render high-quality human avatars with better details, and can reach 120 FPS at 2K resolution on mobile devices.