Comments (2)
Hi Yu,
thank you for your interest in DECA.
Regarding the detail mesh, thank you for the suggestion. We just updated the code to also output the reconstructed mesh with applied displacements. Please pull and try again. To leverage DECA's animatable details, we recommend to follow the provided animation pipeline (see Section 4 of the paper for more information about DECA's animatable details).
Regarding the questions about the paper, there are several factors contributing to the qualitative and quantitative state-of-the-art performance of DECA, namely
- A novel shape consistency loss (Equation 8) that encourages the shape of different images of the same subject to be the same.
- Unlike most previous 3D face reconstruction methods, we use FLAME instead of Basel Face Model (BFM) to represent the coarse shape. FLAME's identity space is more expressive than BFM as demonstrated in Section 7.3 of the original FLAME paper.
- The coarse DECA shape is trained from a large dataset of 2 Million images with a wide coverage of ethnicities (see Appendix A). This makes DECA robust to a large variation of ethnicities, face shapes, head poses, lighting conditions, etc. This is important for a high reconstruction quality.
- The training data are automatically cleaned to avoid poor landmark labels (see Appendix A). We will release the landmark labels for the training data together with the training code in the future.
- The different losses are carefully combined and weighted (see Appendix A). All losses, i.e. landmark loss (Eq. 5), photometric loss, identity loss (Eq. 7), and the shape consistency loss (Eq. 8) contribute to the quality and robustness of the reconstruction.
- It is also worth mentioning the eye closure loss (Eq. 6). While it does not directly influence the reconstruction error on NoW [Sanyal et al. 2019], it makes the reconstructed eye region visually more appealing.
I hope that answers your questions
from deca.
Thanks for your detailed explanation. It really helps.
from deca.
Related Issues (20)
- Notebook is out of date. Could you please update the new version of notebook? HOT 1
- Is this project compatible with a recent GPU ? HOT 9
- no face texture HOT 1
- FileNotFoundError: [Errno 2] No such file or directory: '/ps/scratch/face2d3d/texture_in_the_wild_code/VGGFace2_cleaning_codes/ringnetpp_training_lists/second_cleaning/vggface2_train_list_max_normal_100_ring_5_1_serial.npy' HOT 1
- id loss HOT 1
- The downloaded โdeca_model.tarโ package cannot be decompressed HOT 3
- model.load error HOT 6
- UserWarning: Mtl file does not exist: /data/template.mtl HOT 1
- Dimensions of pose parameters HOT 1
- Steps for setting up the environment in new GPU like 4090
- which software can be used to open this mesh other than meshlab
- How to open in blender HOT 3
- Extracting shape, pose, expression parameters from meshes (3d or 2.5d, not 2d image) HOT 3
- how to use multiview images to fit one FLAME mesh?
- No module named 'pytorch3d.structures'
- AttributeError: module 'inspect' has no attribute 'getargspec'. Did you mean: 'getargs'?
- Got the colorless texture and false training Detail for mesh
- Why do we need to invert the y and z axes?
- face looking down without crop
- How to generate .pkl file along with .ply file as output?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deca.