Fig. 1. 3D Portrait reconstruction methods

Fig. 2. Light Stage device^[35]

Fig. 3. Images captured by Light Stage^[35]

Fig. 4. Facial reflectance function^[35]

Fig. 5. Sampling of facial reflectance function^［35］. (a) Frontal region; (b) right side of chin; (c) junction between cheek and base of the nose; (d) inner part of auricle

Fig. 6. Compute relighting pixel values^[35]

Fig. 7. Face rendered under sampled illumination^[35]

Fig. 8. Generating highly realistic relighting results under various lighting conditions and viewing angles^[5]

Fig. 9. Results of 3D light field display under different lighting conditions^[5]

Fig. 10. Network model flowchart

Fig. 11. 3D light field display effects under different facial expressions

Fig. 12. Overall flowchart of real-time reconstruction-driven portrait

Fig. 13. Light field display results based on eye-tracking^[63]. (a) Public dataset; (b) self-built dataset