# Exploring 3D Face Reconstruction and Fusion Methods for Face Verification: A Case-Study in Video Surveillance

arXiv: https://arxiv.org/abs/2409.10481 · HTML: https://mlsanity.com/paper/2409.10481/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Builds on (most cited first, 15 of 15)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [3D Face Reconstruction by Learning from Synthetic Data](https://mlsanity.com/paper/1609.04387/) (2016)
- [Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images](https://mlsanity.com/paper/2003.08124/) (2020)
- [Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields](https://mlsanity.com/paper/2206.08361/) (2022)
- [Practical Face Reconstruction via Differentiable Ray Tracing](https://mlsanity.com/paper/2101.05356/) (2021)
- [Effective Face Frontalization in Unconstrained Images](https://mlsanity.com/paper/1411.7964/) (2014)
- [SDFR: Synthetic Data for Face Recognition Competition](https://mlsanity.com/paper/2404.04580/) (2024)
- [Survey on 3D face reconstruction from uncalibrated images](https://mlsanity.com/paper/2011.05740/) (2020)
- [Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data](https://mlsanity.com/paper/2404.10378/) (2024)
- [3D Face Reconstruction: the Road to Forensics](https://mlsanity.com/paper/2309.11357/) (2023)
- [Recent Advances in Deep Learning Techniques for Face Recognition](https://mlsanity.com/paper/2103.10492/) (2021)
- [3D Face Reconstruction for Forensic Recognition -- A Survey](https://mlsanity.com/paper/2303.11164/) (2023)
- [An Evaluation of Score Level Fusion Approaches for Fingerprint and Finger-vein Biometrics](https://mlsanity.com/paper/1805.10666/) (2018)

## Built on by (most cited first, 3 of 3)

- [Exploiting Multiple Representations: 3D Face Biometrics Fusion with Application to Surveillance](https://mlsanity.com/paper/2504.18886/) (2025)
- [Comparison of Visual Trackers for Biomechanical Analysis of Running](https://mlsanity.com/paper/2505.04713/) (2025)
- [VideoRun2D Demo: Markerless Body Tracking for Biomechanical Analysis of Running](https://mlsanity.com/paper/2608.19480/) (2026)

## Abstract (arXiv)

3D face reconstruction (3DFR) algorithms are based on specific assumptions tailored to distinct application scenarios. These assumptions limit their use when acquisition conditions, such as the subject's distance from the camera or the camera's characteristics, are different than expected, as typically happens in video surveillance. Additionally, 3DFR algorithms follow various strategies to address the reconstruction of a 3D shape from 2D data, such as statistical model fitting, photometric stereo, or deep learning. In the present study, we explore the application of three 3DFR algorithms representative of the SOTA, employing each one as the template set generator for a face verification system. The scores provided by each system are combined by score-level fusion. We show that the complementarity induced by different 3DFR algorithms improves performance when tests are conducted at never-seen-before distances from the camera and camera characteristics (cross-distance and cross-camera settings), thus encouraging further investigations on multiple 3DFR-based approaches.