Comments (6)
Hi, I tried to implement the facial reenactment and got the results below. But they don't look as neat as Fig.7 in the paper.
I use person_1
as target and person_2
as driving. I added custom_seq_driving before line 367 in eval_transformed_rays.py to compute the transferred expressions and poses. Then I use the obtained expressions and poses inside the for loop.
I tried either transferring the raw expressions or the expression deltas (where I manually choose frame 973 in person_1
and frame 990 in person_2
as neutral expression).
- Results by directly transferring expression (by setting transfer_delta_expressions_from_netural to
False
.)
out.mp4
- Results by transferring expression delta (by setting transfer_delta_expressions_from_netural to
True
.)
transferred.mp4
Any help and suggestion will be appreciated. Thanks for your time!
from 4d-facial-avatars.
Hey, if you use the expressions and poses from one actor with a trained model of another, you will basically get reenactment.
There are a few things to be careful with:
- provide the correct background image you want to use
- the expression and face identity coefficients are quite entangled (this is inherent in the 3DMM face model), so instead of using the expressions themselves, it looks better if you just transfer the 'expression delta' from one person's "neutral expression" to the other person's "netural expression". This logic for this is in real_to_nerf.py.
- If you go for head angles that are beyond the angles in the training of the model, it obviously won't look good.
from 4d-facial-avatars.
Thanks for the reply, is there any plan to release related code in the near future?
from 4d-facial-avatars.
Hi, I tried to implement the facial reenactment and got the results below. But they don't look as neat as Fig.7 in the paper.
I use
person_1
as target andperson_2
as driving. I added custom_seq_driving before line 367 in eval_transformed_rays.py to compute the transferred expressions and poses. Then I use the obtained expressions and poses inside the for loop.I tried either transferring the raw expressions or the expression deltas (where I manually choose frame 973 in
person_1
and frame 990 inperson_2
as neutral expression).
Results by directly transferring expression (by setting transfer_delta_expressions_from_netural to
False
.)Results by transferring expression delta (by setting transfer_delta_expressions_from_netural to
True
.)Any help and suggestion will be appreciated. Thanks for your time!
Hi Thanks for sharing the solution. But I meet the index out of bound error when I add code before line 367. Could you share more information how should I change the code? Thanks.
_, posesD, _, _, _, expressionsD, _, _ = load_flame_data(
"nerface_dataset/person_2",
half_res=cfg.dataset.half_res,
testskip=cfg.dataset.testskip, test=True) #i_train, i_val, i_test = i_split
i_test = i_split
rigid_poses_driving = posesD[i_test].float().to(device)
expressions_driving = expressionsD[i_test].float().to(device)
render_expressions,render_poses = custom_seq_driving(rigid_poses_driving,render_poses,expressions_driving,render_expressions)
from 4d-facial-avatars.
Hi, I tried to implement the facial reenactment and got the results below. But they don't look as neat as Fig.7 in the paper.
I useperson_1
as target andperson_2
as driving. I added custom_seq_driving before line 367 in eval_transformed_rays.py to compute the transferred expressions and poses. Then I use the obtained expressions and poses inside the for loop.
I tried either transferring the raw expressions or the expression deltas (where I manually choose frame 973 inperson_1
and frame 990 inperson_2
as neutral expression).
- Results by directly transferring expression (by setting transfer_delta_expressions_from_netural to
False
.)- Results by transferring expression delta (by setting transfer_delta_expressions_from_netural to
True
.)Any help and suggestion will be appreciated. Thanks for your time!
Hi Thanks for sharing the solution. But I meet the index out of bound error when I add code before line 367. Could you share more information how should I change the code? Thanks. _, posesD, _, _, _, expressionsD, _, _ = load_flame_data( "nerface_dataset/person_2", half_res=cfg.dataset.half_res, testskip=cfg.dataset.testskip, test=True) #i_train, i_val, i_test = i_split i_test = i_split rigid_poses_driving = posesD[i_test].float().to(device) expressions_driving = expressionsD[i_test].float().to(device) render_expressions,render_poses = custom_seq_driving(rigid_poses_driving,render_poses,expressions_driving,render_expressions)
from 4d-facial-avatars.
Hi, I tried to implement the facial reenactment and got the results below. But they don't look as neat as Fig.7 in the paper.
I useperson_1
as target andperson_2
as driving. I added custom_seq_driving before line 367 in eval_transformed_rays.py to compute the transferred expressions and poses. Then I use the obtained expressions and poses inside the for loop.
I tried either transferring the raw expressions or the expression deltas (where I manually choose frame 973 inperson_1
and frame 990 inperson_2
as neutral expression).
- Results by directly transferring expression (by setting transfer_delta_expressions_from_netural to
False
.)- Results by transferring expression delta (by setting transfer_delta_expressions_from_netural to
True
.)Any help and suggestion will be appreciated. Thanks for your time!
Hi Thanks for sharing the solution. But I meet the index out of bound error when I add code before line 367. Could you share more information how should I change the code? Thanks. _, posesD, _, _, _, expressionsD, _, _ = load_flame_data( "nerface_dataset/person_2", half_res=cfg.dataset.half_res, testskip=cfg.dataset.testskip, test=True) #i_train, i_val, i_test = i_split i_test = i_split rigid_poses_driving = posesD[i_test].float().to(device) expressions_driving = expressionsD[i_test].float().to(device) render_expressions,render_poses = custom_seq_driving(rigid_poses_driving,render_poses,expressions_driving,render_expressions)
Have you solved this problem yet?
from 4d-facial-avatars.
Related Issues (20)
- A problem about the test results HOT 1
- How to get the bounding box? HOT 1
- results is incorrect when using render_debug_camera_matrix HOT 1
- Getting cuda memory issue. How to resolve this error? HOT 2
- Question about the translation vector HOT 2
- Question about the coordinate system
- Which ".yml" file is used to build the environment?
- index out of bounds HOT 1
- How to change the pose and expression during evaluation? HOT 1
- IndexError HOT 1
- for customized data preprocessing, how to generate the required shape expression vector?
- which repo you used in quantitative evaluation for DVP(Deep Video Portrait)? HOT 2
- How much RAM required for training? HOT 1
- Qualitative results different from paper: Blurry shoulders HOT 1
- Question about Test speed HOT 3
- Could this project be trained on multi-gpus? HOT 1
- Huge Artifacts occured in cross-id face reenactment results HOT 4
- about model of nerf
- How to accelerate the training process
- About index_map.npy HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from 4d-facial-avatars.