Comments (6)
Hi, the extracted surface looks suspicious in both setups. Can you confirm the latest commit is used? If so, the recent eikonal loss update may be the culprit. The original paper did not use eikonal loss. It seems eikonal loss moved the 0 isosurface inside the actual one.
There are two ways to fix it:
(1) Without re-train the model. Remove --mc_threshold 0
in scripts/render_mgpu.sh
, and run that script again. This will use the default marching cubes threshold --mc_threshold=-0.002
.
(2) Re-train the model without eikonal loss. To do so, you can roll back to the commit before this one.
from banmo.
The experiments in the paper are before this commit, so I think both fixing the bugs in the lbs implementation and replacing feature matching loss with feature rendering loss might have helped.
The --mc_threshold
is the default value -0.002
for experiments in the paper.
from banmo.
Hi, the results of this repo should be aligned with the camera-ready version, where Tab. 1 got updated for all entries.
However, I wouldn't expect the performance to drop when training setup 1., compared to setup 3. Does it visually look worse?
from banmo.
Thanks you for your answer.
I just downloaded papers from arxiv, so I didn't know camera-ready version. I will refer to this paper. Then, result of AMA setup2 makes sense.
AMA setup 1 look worse than setup 3. Specifically, at mesh visualization, details of leg and skirt are more accurate in setup 3 than setup 1.
I will attach reference images below. (meshes are visualized by MeshLab)
T_samba1-mesh-00000.obj from setup1
T_samba1-mesh-00000.obj from setup3
T_swing1-mesh-00000.obj from setup1
T_swing1-mesh-00000.obj from setup3
from banmo.
Hi
I'm sorry for late reply
(1) makes better visualization results, which are plausible and simlar to paper's figure 4.
After re-rendering without --mc-threhsold, I also ran evaluation script again and got better ave chamfer distance (ave 8.2), which is even lower than 9.2 (indicated in Paper Table1.)
I confirmed that I just cloned your latest commit version and trained models without eikonal loss because default eikonal loss weight is 0.
Then, I have some questions.
-
Is there any additive loss function or techique which is not used at paper version's implementation? I wonder why I got better score than camera-ready version paper. Is there an possibility that some randomness like ray sampling or data fetching affect result?
-
I want to know exact
--mc-threshold
when you rendered results for Table 1. It seems that chamfer distance is quite dependent on this hyperparameter.
I would like to hear your opinion concerning those.
Best regards.
from banmo.
My questions have been resolved.
Thank you for answers and sharing nice work.
from banmo.
Related Issues (20)
- Questions about the synthetic datasets HOT 9
- Training BANMo using my own videos HOT 6
- SOS, the cat is so cute~~~~~ I cannot focused on codes! o(=•ェ•=)m
- bones_dfm or bones_rst when using gauss_mlp_skinning? HOT 2
- Canonical embeddings matching HOT 6
- Questions on the evaluation on root pose prediction HOT 2
- Question for Nerfies experiment HOT 6
- Question about mesh of Viser in Banmo HOT 2
- Generation of synthetic datasets HOT 3
- No "from pytorch3d import _C"
- Visualize of articulated shape HOT 1
- Optimized models on dropbox HOT 2
- update_delta_rts
- Bone reinitialization HOT 1
- Volume rendering HOT 2
- Questions by using pre-optimized models HOT 7
- issue of "tmp/nvs-5-0-traj-all.mp4: No such file or directory" when trying pre-optimized models HOT 6
- some problem with colab demo HOT 1
- can banmo be used for 3D reconstruction of birds? HOT 4
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 banmo.