# SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Images

Source: [SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Images](<https://www.sota2.com/research/paper/68fa777a1e209131cea73727>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:39:48.939Z

Authors: Daisheng Jin, Jiangbei Hu, Baixin Xu, Yuxin Dai, Chen Qian, Ying He

Published: 2023-12-11T03:14:58.000Z

## Abstract

In this study, we introduce a novel two-stage technique for decomposing and reconstructing facial features from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual. To synthesize 3D facial models more realistically, we endeavor to decouple key facial attributes from the RGB color, including geometry, diffuse reflectance, and specular reflectance. Specifically, we design a Sparse-view Face Decomposition Model (SFDM): 1) In the first stage, we create a general facial template from a wide array of individual faces, encapsulating essential geometric and reflectance characteristics. 2) Guided by this template, we refine a specific facial model for each individual in the second stage, considering the interaction between geometry and reflectance, as well as the effects of subsurface scattering on the skin. With these advances, our method can reconstruct high-quality facial representations from as few as three images. The comprehensive evaluation and comparison reveal that our approach outperforms existing methods by effectively disentangling geometric and reflectance components, significantly enhancing the quality of synthesized novel views, and paving the way for applications in facial relighting and reflectance editing.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Face Reconstruction and Decomposition on FaceScape 5 views (sparse views)](<https://www.sota2.com/research/sota/3d-face-reconstruction-and-decomposition-on-facescape-5-views-sparse-views.md>): 3D Face Reconstruction and Decomposition; FaceScape 5 views (sparse views); PSNR: 26.73.

- [3D Face Reconstruction and Decomposition on FaceScape 10 views (sparse views)](<https://www.sota2.com/research/sota/3d-face-reconstruction-and-decomposition-on-facescape-10-views-sparse-views.md>): 3D Face Reconstruction and Decomposition; FaceScape 10 views (sparse views); PSNR: 27.64.

- [3D Face Reconstruction and Decomposition on FaceScape 3 views sparse views](<https://www.sota2.com/research/sota/3d-face-reconstruction-and-decomposition-on-facescape-3-views-sparse-views.md>): 3D Face Reconstruction and Decomposition; FaceScape 3 views sparse views; PSNR: 25.54.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.06085>)

[PDF](<https://arxiv.org/pdf/2312.06085.pdf>)