# mitsuba RealFaceDB Rendering **Repository Path**: du-youyang/mitsuba-RealFaceDB-rendering ## Basic Information - **Project Name**: mitsuba RealFaceDB Rendering - **Description**: Using Mitsuba3 Render the patch-style texture given by RealFaceDB. - **Primary Language**: Python - **License**: Apache-2.0 - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2023-02-21 - **Last Updated**: 2023-03-02 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # RealFaceDB Rendering ## Introduction Using Mitsuba3 Render the patch-style texture given by RealFaceDB. \ Using Pytorch to render RealFaceDB texture directly within texture-space. SSS is already supported. > Notice that SSS is really high-overhead, and cannot get apparent result from it, since the diffuse normal is low-frequency. ## Getting Start Mitsuba implementation please refer to > mitsuba_implementation/AvatarMeDatasetRenderer.py Pytorch_implementation please refer to > pytorch_implementation/pytorch_RealFaceDB_render.py Pytorch-version's work flow: ![D42663D502F5869F6BAF6E651A3E6348](README.assets\D42663D502F5869F6BAF6E651A3E6348.jpg) ## Data The texture data used in this project come from RealFaceDB, presented by following paper: > @InProceedings{lattas2020avatarme, \ author = {Lattas, Alexandros and Moschoglou, Stylianos and Gecer, Baris and Ploumpis, Stylianos and Triantafyllou, Vasileios and Ghosh, Abhijeet and Zafeiriou, Stefanos}, \ title = {AvatarMe: Realistically Renderable 3D Facial Reconstruction "In-the-Wild"}, \ booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, \ month = {June}, \ year = {2020} } > > @article{lattas2021avatarme++,\ title={AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANs},\ author={Lattas, Alexandros and Moschoglou, Stylianos and Ploumpis, Stylianos and Gecer, Baris and Ghosh, Abhijeet and Zafeiriou, Stefanos P},\ journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},\ year={2021},\ publisher={IEEE}\ } or you may need to access this link : [AvatarMe++](https://github.com/lattas/avatarme)