Summary of Depth Map Denoising Network and Lightweight Fusion Network For Enhanced 3d Face Recognition, by Ruizhuo Xu et al.
Depth Map Denoising Network and Lightweight Fusion Network for Enhanced 3D Face Recognition
by Ruizhuo Xu, Ke Wang, Chao Deng, Mei Wang, Xi Chen, Wenhui Huang, Junlan Feng, Weihong Deng
First submitted to arxiv on: 1 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to 3D face recognition (FR) using consumer depth sensors. The sensors produce coarse and noisy data, making it challenging to use directly. To address this issue, the authors introduce an innovative Depth map denoising network (DMDNet) based on Denoising Implicit Image Function (DIIF). This network reduces noise and enhances the quality of facial depth images for low-quality 3D FR. The authors also design a powerful recognition network called Lightweight Depth and Normal Fusion network (LDNFNet), which combines multi-branch fusion block to learn unique features from different modalities, including depth and normal images. Experimental results on four distinct databases demonstrate the effectiveness and robustness of the proposed methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us recognize faces better using special cameras that take 3D pictures. These cameras make noisy pictures, which makes it hard to use them directly. The authors created a new way to clean up these pictures called DMDNet. Then they made another tool called LDNFNet that uses different types of images to recognize faces. They tested their methods on four different databases and got great results. |
Keywords
» Artificial intelligence » Face recognition
