# Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction

arXiv: https://arxiv.org/abs/2402.19197 · HTML: https://mlsanity.com/paper/2402.19197/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 21 of 21)

- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [Multi-Garment Net: Learning to Dress 3D People from Images](https://mlsanity.com/paper/1908.06903/) (2019)
- [PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction](https://mlsanity.com/paper/2007.03858/) (2020)
- [Deep Appearance Models for Face Rendering](https://mlsanity.com/paper/1808.00362/) (2018)
- [Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing](https://mlsanity.com/paper/2204.08906/) (2022)
- [BCNet: Learning Body and Cloth Shape from A Single Image](https://mlsanity.com/paper/2004.00214/) (2020)
- [Detailed, accurate, human shape estimation from clothed 3D scan sequences](https://mlsanity.com/paper/1703.04454/) (2017)
- [SiCloPe: Silhouette-Based Clothed People](https://mlsanity.com/paper/1901.00049/) (2018)
- [StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision](https://mlsanity.com/paper/2104.05289/) (2021)
- [Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms](https://mlsanity.com/paper/2209.10529/) (2022)
- [IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-view Human Reconstruction](https://mlsanity.com/paper/2211.07955/) (2022)
- [Towards Robust and Expressive Whole-body Human Pose and Shape Estimation](https://mlsanity.com/paper/2312.08730/) (2023)

## Built on by (most cited first, 1 of 1)

- [MVD-HuGaS: Human Gaussians from a Single Image via 3D Human Multi-view Diffusion Prior](https://mlsanity.com/paper/2503.08218/) (2025)

## Abstract (arXiv)

Pixel-aligned implicit models, such as PIFu, PIFuHD, and ICON, are used for single-view clothed human reconstruction. These models need to be trained using a sampling training scheme. Existing sampling training schemes either fail to capture thin surfaces (e.g. ears, fingers) or cause noisy artefacts in reconstructed meshes. To address these problems, we introduce Fine Structured-Aware Sampling (FSS), a new sampling training scheme to train pixel-aligned implicit models for single-view human reconstruction. FSS resolves the aforementioned problems by proactively adapting to the thickness and complexity of surfaces. In addition, unlike existing sampling training schemes, FSS shows how normals of sample points can be capitalized in the training process to improve results. Lastly, to further improve the training process, FSS proposes a mesh thickness loss signal for pixel-aligned implicit models. It becomes computationally feasible to introduce this loss once a slight reworking of the pixel-aligned implicit function framework is carried out. Our results show that our methods significantly outperform SOTA methods qualitatively and quantitatively. Our code is publicly available at https://github.com/kcyt/FSS.