Dezhi Kong's scientific contributions

What is this page?


This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.

It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.

If you're a ResearchGate member, you can follow this page to keep up with this author's work.

If you are this author, and you don't want us to display this page anymore, please let us know.

Publications (1)


Fig. 1. Overview of the framework Training stage is as follows: 1) We get the original data of 3D coordinates by 3D data files. 2) According to the acquired 3D data, we recover the corresponding 2D facial image. 3) We extract the feature points to establish 2D database for each 2D facial image. 4) Based on the 2D feature points, the face will be divided into several triangular regions.
Fig. 2. The recovered image by 3D model
Fig. 4. The relation of weights between angle and scale ratio
Effective 3D face depth estimation from a single 2D face image
  • Conference Paper
  • Full-text available

September 2016

·

1,187 Reads

·

9 Citations

Dezhi Kong

·

·

Yun-Xia Liu

·

[...]

·

Hongying Jia
Download
Share

Citations (1)


... Facial depth estimation has many applications and approaches using both conventional and traditional methodologies [8]. Using the feature extraction methods, There are many SoA potential solutions to predict facial depth [16]- [22]. Facial feature extraction depth maps can help in the advancement of facial depth tasks. ...

Reference:

A Robust Light-Weight Fused-Feature Encoder-Decoder Model for Monocular Facial Depth Estimation From Single Images Trained on Synthetic Data
Effective 3D face depth estimation from a single 2D face image