Skip to content

Commit b8153de

Browse files
committed
training code
1 parent 234c20c commit b8153de

25 files changed

+1080603
-343
lines changed

.gitignore

+1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,5 @@
11
data/*/*
2+
data/thuman*
23
!data/tbfo.ttf
34
__pycache__
45
debug/

README.md

+12-3
Original file line numberDiff line numberDiff line change
@@ -39,6 +39,7 @@
3939
<br />
4040

4141
## News :triangular_flag_on_post:
42+
- [2022/05/15] Training code is released, please check [Training Instruction](docs/training.md).
4243
- [2022/04/26] <a href="https://github.com/Jeff-sjtu/HybrIK">HybrIK (SMPL)</a> is supported as optional HPS by <a href="https://jeffli.site/">Jiefeng Li</a>.
4344
- [2022/03/05] <a href="https://github.com/YadiraF/PIXIE">PIXIE (SMPL-X)</a>, <a href="https://github.com/mkocabas/PARE">PARE (SMPL)</a>, <a href="https://github.com/HongwenZhang/PyMAF">PyMAF (SMPL)</a> are all supported as optional HPS.
4445
- [2022/02/07] <a href='https://colab.research.google.com/drive/1-AWeWhPvCTBX0KfMtgtMk10uPU05ihoA?usp=sharing' style='padding-left: 0.5rem;'><img src='https://colab.research.google.com/assets/colab-badge.svg' alt='Google Colab'></a> is ready to use.
@@ -119,9 +120,14 @@
119120
- [x] colab notebook <a href='https://colab.research.google.com/drive/1-AWeWhPvCTBX0KfMtgtMk10uPU05ihoA?usp=sharing' style='padding-left: 0.5rem;'>
120121
<img src='https://colab.research.google.com/assets/colab-badge.svg' alt='Google Colab'>
121122
</a>
122-
- [x] dataset processing pipeline
123-
- [ ] training and evaluation codes
124-
- [ ] Video-to-Avatar module
123+
- [x] dataset processing
124+
- [x] RGB/Normal Rendering
125+
- [x] Visibility computing
126+
- [ ] training codes
127+
- [x] ICON (w/ & w/o global encoder, w/ SMPL-X)
128+
- [x] PIFu* (RGB image + predicted normal map as input)
129+
- [ ] PaMIR* (RGB image + predicted normal map as input, w/ voxelized SMPL)
130+
- [ ] evaluation on CAPE (Hard, Easy)
125131

126132

127133
## Installation
@@ -132,6 +138,9 @@ Please follow the [Installation Instruction](docs/installation.md) to setup all
132138

133139
Please follow the [Data Preprocess Instruction](docs/dataset.md) to generate the train/val/test dataset from raw scans (THuman2.0).
134140

141+
## Training
142+
Please follow the [Training Instruction](docs/training.md) to train your own model using THuman2.0.
143+
135144
## Demo
136145

137146
```bash

0 commit comments

Comments
 (0)