# SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images

arXiv: https://arxiv.org/abs/2006.03630 · HTML: https://mlsanity.com/paper/2006.03630/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2020.

## Built on by (most cited first, 16 of 16)

- [Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation](https://mlsanity.com/paper/2401.08559/) (2024)
- [EventHPE: Event-based 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2108.06819/) (2021)
- [Action2video: Generating Videos of Human 3D Actions](https://mlsanity.com/paper/2111.06925/) (2021)
- [Human Pose and Shape Estimation from Single Polarization Images](https://mlsanity.com/paper/2108.06834/) (2021)
- [CBARF: Cascaded Bundle-Adjusting Neural Radiance Fields from Imperfect Camera Poses](https://mlsanity.com/paper/2310.09776/) (2023)
- [MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering](https://mlsanity.com/paper/2403.18820/) (2024)
- [GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain](https://mlsanity.com/paper/2503.22397/) (2025)
- [CARE-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson's Disease Gait Assessment](https://mlsanity.com/paper/2510.04312/) (2025)
- [Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HAR](https://mlsanity.com/paper/2402.14427/) (2024)
- [HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features](https://mlsanity.com/paper/2411.03086/) (2024)
- [Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation](https://mlsanity.com/paper/2202.03074/) (2022)
- [PHD: Personalized 3D Human Body Fitting with Point Diffusion](https://mlsanity.com/paper/2508.21257/) (2025)
- [On the Skinning of Gaussian Avatars](https://mlsanity.com/paper/2509.11411/) (2025)
- [Real-Time Animatable 2DGS-Avatars with Detail Enhancement from Monocular Videos](https://mlsanity.com/paper/2505.00421/) (2025)
- [Refining Diffusion Models for Motion Synthesis with an Acceleration Loss to Generate Realistic IMU Data](https://mlsanity.com/paper/2512.08859/) (2025)
- [Mocap Anywhere: Towards Pairwise-Distance based Motion Capture in the Wild (for the Wild)](https://mlsanity.com/paper/2601.19519/) (2026)

## Abstract (arXiv)

In this paper, we propose a novel approach to reconstruct 3D human body shapes based on a sparse set of RGBD frames using a single RGBD camera. We specifically focus on the realistic settings where human subjects move freely during the capture. The main challenge is how to robustly fuse these sparse frames into a canonical 3D model, under pose changes and surface occlusions. This is addressed by our new framework consisting of the following steps. First, based on a generative human template, for every two frames having sufficient overlap, an initial pairwise alignment is performed; It is followed by a global non-rigid registration procedure, in which partial results from RGBD frames are collected into a unified 3D shape, under the guidance of correspondences from the pairwise alignment; Finally, the texture map of the reconstructed human model is optimized to deliver a clear and spatially consistent texture. Empirical evaluations on synthetic and real datasets demonstrate both quantitatively and qualitatively the superior performance of our framework in reconstructing complete 3D human models with high fidelity. It is worth noting that our framework is flexible, with potential applications going beyond shape reconstruction. As an example, we showcase its use in reshaping and reposing to a new avatar.