diff --git a/Readme.md b/Readme.md index 9595633..f59a0d9 100644 --- a/Readme.md +++ b/Readme.md @@ -2,7 +2,7 @@ * @Date: 2021-01-13 20:32:12 * @Author: Qing Shuai * @LastEditors: Qing Shuai - * @LastEditTime: 2021-06-04 17:12:01 + * @LastEditTime: 2021-06-14 16:41:00 * @FilePath: /EasyMocapRelease/Readme.md --> @@ -21,7 +21,7 @@ [![report](https://img.shields.io/badge/quickstart-green)](./doc/quickstart.md) -This is the basic code for fitting SMPL[1]/SMPL+H[2]/SMPL-X[3] model to capture body+hand+face poses from multiple views. +This is the basic code for fitting SMPL[1]/SMPL+H[2]/SMPL-X[3]/MANO[2] model to capture body+hand+face poses from multiple views.
@@ -29,6 +29,12 @@ This is the basic code for fitting SMPL[1]/SMPL+H[2]/SMPL-X[3] model to capture Videos are from ZJU-MoCap, with 23 calibrated and synchronized cameras.
+
+ +
+ Captured with 8 cameras. +
+ ### Internet video with a mirror [![report](https://img.shields.io/badge/CVPR21-mirror-red)](https://arxiv.org/pdf/2104.00340.pdf) [![quickstart](https://img.shields.io/badge/quickstart-green)](https://github.com/zju3dv/Mirrored-Human) @@ -62,11 +68,15 @@ This is the basic code for fitting SMPL[1]/SMPL+H[2]/SMPL-X[3] model to capture Captured with 4 consumer cameras -### Others +### Novel view synthesis from sparse views +[![report](https://img.shields.io/badge/CVPR21-neuralbody-red)](https://arxiv.org/pdf/2012.15838.pdf) [![quickstart](https://img.shields.io/badge/quickstart-green)](https://github.com/zju3dv/neuralbody) -This project is used by many other projects: +
+
+
+ Captured with 8 consumer cameras +
-- [[CVPR21] Dense Reconstruction and View Synthesis from **Sparse Views**](https://zju3dv.github.io/neuralbody/) ## Other features @@ -78,8 +88,9 @@ This project is used by many other projects: ## Updates -- 06/04/2021: The **real-time 3D visualization** part is released! -- 04/12/2021: Mirrored-Human part is released. We also release the calibration tool and the annotator. +- 06/10/2021: The **real-time 3D visualization** part is released! +- 04/11/2021: The calibration tool and the annotator are released. +- 04/11/2021: **Mirrored-Human** part is released. ## Installation @@ -103,7 +114,7 @@ Here are the great works this project is built upon: - `easymocap/estimator/YOLOv4`: an object detector[6](Coming soon) - `easymocap/estimator/HRNet` : a 2D human pose estimator[7](Coming soon) -We also would like to thank Wenduo Feng who is the performer in the sample data. +We also would like to thank Wenduo Feng, Di Huang, Yuji Chen, Hao Xu, Qing Shuai, Qi Fang, Ting Xie, Junting Dong, Sida Peng and Xiaopeng Ji who are the performers in the sample data. ## Contact diff --git a/doc/feng/mano.gif b/doc/feng/mano.gif new file mode 100644 index 0000000..318ea4d Binary files /dev/null and b/doc/feng/mano.gif differ diff --git a/doc/neuralbody/sida-frame0.jpg b/doc/neuralbody/sida-frame0.jpg new file mode 100644 index 0000000..b32a3f2 Binary files /dev/null and b/doc/neuralbody/sida-frame0.jpg differ diff --git a/doc/neuralbody/sida.gif b/doc/neuralbody/sida.gif new file mode 100644 index 0000000..c16a68f Binary files /dev/null and b/doc/neuralbody/sida.gif differ diff --git a/doc/quickstart.md b/doc/quickstart.md index c50455b..eae3453 100644 --- a/doc/quickstart.md +++ b/doc/quickstart.md @@ -2,7 +2,7 @@ * @Date: 2021-04-02 11:53:16 * @Author: Qing Shuai * @LastEditors: Qing Shuai - * @LastEditTime: 2021-05-27 20:15:52 + * @LastEditTime: 2021-06-14 14:26:19 * @FilePath: /EasyMocapRelease/doc/quickstart.md --> # Quick Start @@ -13,17 +13,16 @@ We provide an example multiview dataset[[dropbox](https://www.dropbox.com/s/24mb ```bash data=path/to/data -out=path/to/output # 0. extract the video to images python3 scripts/preprocess/extract_video.py ${data} --handface # 2.1 example for SMPL reconstruction -python3 apps/demo/mv1p.py ${data} --out ${out}/smpl --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --vis_smpl +python3 apps/demo/mv1p.py ${data} --out ${data}/output/smpl --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --vis_smpl # 2.2 example for SMPL-X reconstruction -python3 apps/demo/mv1p.py ${data} --out ${out}/smplx --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --body bodyhandface --model smplx --gender male --vis_smpl +python3 apps/demo/mv1p.py ${data} --out ${data}/output/smplx --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --body bodyhandface --model smplx --gender male --vis_smpl # 2.3 example for MANO reconstruction # MANO model is required for this part -python3 apps/demo/mv1p.py ${data} --out ${out}/manol --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --body handl --model manol --gender male --vis_smpl -python3 apps/demo/mv1p.py ${data} --out ${out}/manor --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --body handr --model manor --gender male --vis_smpl +python3 apps/demo/mv1p.py ${data} --out ${data}/output/manol --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --body handl --model manol --gender male --vis_smpl +python3 apps/demo/mv1p.py ${data} --out ${data}/output/manor --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --body handr --model manor --gender male --vis_smpl ``` # Demo On Your Dataset