Comments (5)
Hi! Thank you for your feedback!
Actually, we've only implemented code to run Animatable NeRF on fitted SMPL and ground truth images. I haven't tested whether using other model works under current pipeline. Although at first glance CAPE and SMPL have similar topology, thus it would probably work without too much pain (and probably improve the reconstruction since CAPE fits clothed human better).
prepare_lbs_meta.py
will prepare input files under the lbs
folder of the corresponding dataset. And as the script's name suggests, it will prepare metadata to perform LBS on the fitted SMPL of the dataset in question. The outputs weights.npy
, joints.npy
, tvertices.npy
and bigpose_vertices.npy
correspond to the SMPL model fitted to the data instead of the dataset itself.
I'm not sure I fully understand what your problem is so it would be great if you elaborate on what do you mean by:
But I find the result of get_tpose_blend_weights() seems not right
From the image you posted I can see that the posed vertices actually contains pose-dependent deformation (Notice the bulging on the elbows). Thus when you unpose the posed mesh, you should also remove the pose-dependent deformation of CAPE to get the original canonical mesh. In Animtable NeRF we simply ignore the pose-dependent effect of SMPL (When converting SMPL from canonical to world space, we only apply LBS without pose-dependent deformation), so this phenomenon of bulging elbow is kind of expected. I would advise using the provided GT canonical mesh and pose it to world space without pose-denpendent effect (you'll notice some bulging or contraction on the posed mesh).
We're planning on improving documentation about preparing your custom dataset but I haven't been able to find time for that.
from animatable_nerf.
I see... So the data param processing is correct, right?
from animatable_nerf.
Looks good enough to me. But you should be aware of the caveats mentioned in my previous comment #47 (comment) when proceeding.
from animatable_nerf.
Hi, @dendenxu , sorry to bother you again. I'm confused about the z_vals
in the code. Whether it refers to the distance along the ray or the distance on the z-coordinate axis?Its performance in depth_map
and tpose_nerf_network.py looks contradictory.
from animatable_nerf.
@tpzou No big deal. z_vals
means distance along the ray (consider world coordinates). We called it z_vals
(and use it to compute the depth map) because we consider depth as originating from the camera center, instead of the camera plane (perspective v.s. orthogonal projection).
from animatable_nerf.
Related Issues (20)
- The missing code about implementing NT method HOT 1
- Is there any way that I can color the model I've generated? HOT 1
- 关于变换矩阵的计算 HOT 1
- Sdf
- Could you update the pretrained models for ZJU-mocap dataset? HOT 1
- question about the way to compute alpha in AniSDF HOT 1
- 自制数据集时如何获取animatable_nerf数据集中的'lbs'文件夹下的所有文件呢 HOT 1
- Is it possible to synthesize novel poses on trained model(extended version)? HOT 8
- question about novel pose generation in SDF-PDF HOT 3
- (New Actions) - Vertices and Params for H36m dataset
- How long does it take to train a model? HOT 1
- Per-subject scores of ZJU-Mocap and Ckpts for the other five subjects HOT 2
- Number of cameras in ZJU-Mocap HOT 1
- Test cameras in ZJU differ from the description in the papers HOT 4
- Testing Pretrained Models HOT 4
- How to render normal image HOT 6
- motion sequence-driven HOT 1
- The content in the 'tools' folder is incomplete.
- How to render human under novel poses? HOT 2
- The render result is completely black with no person
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 animatable_nerf.