Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis - ER-NeRF/main.py at main · ishine/ER-NeRF
wget https://github.com/YudongGuo/AD-NeRF/blob/master/data_util/face_tracking/3DMM/exp_info.npy?raw=true -O data_utils/face_tracking/3DMM/exp_info.npy wget https://github.com/YudongGuo/AD-NeRF/blob/master/data_util/face_tracking/3DMM/keys_info.npy?raw=true -O data_utils/face_trac...
https://github.com/Fictionarry/ER-NeRF/tree/main?tab=readme-ov-file 下载官方仓库 使用cmd 根据github,下载对应的依赖,python版本,模型等 github官网教程 为ernerf创建虚拟环境 使用miniconda 激活ernerf虚拟环境 使用miniconda 为ernerf下载pytorch 使用miniconda 为ernerf下载依赖 使用miniconda 为ernerf下载pytorch...
[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis - ER-NeRF/encoding.py at main · merthmagic/ER-NeRF
wget https://github.com/YudongGuo/AD-NeRF/blob/master/data_util/face_tracking/3DMM/exp_info.npy?raw=true -O data_utils/face_tracking/3DMM/exp_info.npy wget https://github.com/YudongGuo/AD-NeRF/blob/master/data_util/face_tracking/3DMM/keys_info.npy?raw=true -O data_utils/face_trac...
wget https://github.com/YudongGuo/AD-NeRF/blob/master/data_util/face_tracking/3DMM/exp_info.npy?raw=true -O data_utils/face_tracking/3DMM/exp_info.npy wget https://github.com/YudongGuo/AD-NeRF/blob/master/data_util/face_tracking/3DMM/keys_info.npy?raw=true -O data_utils/face_trac...
[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis - ER-NeRF/requirements.txt at main · merthmagic/ER-NeRF
(ernerf)john@debian:~/ER-NeRF$ wget https://github.com/YudongGuo/AD-NeRF/blob/master/data_util/face_parsing/79999_iter.pth?raw=true -O data_utils/face_parsing/79999_iter.pth (ernerf)john@debian:~/ER-NeRF$ wget https://github.com/YudongGuo/AD-NeRF/blob/master/data_util/face_tracki...
the head pose into spatial coordinates. Extensive experiments demonstrate that our method renders better high-fidelity and audio-lips synchronized talking portrait videos, with realistic details and high efficiency compared to previous methods. Code is available athttps://github.com/Fictionarry/ER-NeRF....
代码:https://github.com/Fictionarry/ER-NeRF Abstract 本文提出一种新的基于 condition NeRF 的 talking portrait 合成框架 ER-NeRF,可以在较小的参数量下实现高精度的实时渲染和快速收敛。我们的想法是显示利用空间区域的不平等贡献来指导谈话肖像建模。具体而言,为了提高动态头部重建的准确性,通过使用三个2D哈希编...