From 902c5818146591c8dc800b6318e3443dfbed362b Mon Sep 17 00:00:00 2001 From: "sq@114" Date: Sun, 8 May 2022 19:55:56 +0800 Subject: [PATCH] :memo: add demo gif --- Readme.md | 43 ++++++++++++++++++++++++------------------- 1 file changed, 24 insertions(+), 19 deletions(-) diff --git a/Readme.md b/Readme.md index 6b6d8f1..c2a2482 100644 --- a/Readme.md +++ b/Readme.md @@ -32,13 +32,23 @@ This is the basic code for fitting SMPL[^loper2015]/SMPL+H[^romero2017]/SMPL-X[^

- Videos are from ZJU-MoCap, with 23 calibrated and synchronized cameras. + Videos are from ZJU-MoCap, with 23 calibrated and synchronized cameras.

- Captured with 8 cameras. + Captured with 8 cameras. +
+ +### Internet video(Coming soon) + +This part is the basic code for fitting SMPL[^loper2015] with 2D keypoints estimation[^cao2018,^hrnet] and CNN initialization[^kolotouros2019]. + +
+ +
+ The raw video is from Youtube.
### Internet video with a mirror @@ -48,13 +58,9 @@ This is the basic code for fitting SMPL[^loper2015]/SMPL+H[^romero2017]/SMPL-X[^

- The raw video is from Youtube. + The raw video is from Youtube.
-
-
- Captured with 6 cameras and a mirror -
### Multiple Internet videos with a specific action (Coming soon) @@ -62,7 +68,7 @@ This is the basic code for fitting SMPL[^loper2015]/SMPL+H[^romero2017]/SMPL-X[^

- Internet videos of Roger Federer's serving + Internet videos of Roger Federer's serving
### Multiple views of multiple people @@ -71,21 +77,20 @@ This is the basic code for fitting SMPL[^loper2015]/SMPL+H[^romero2017]/SMPL-X[^

- Captured with 8 consumer cameras + Captured with 8 consumer cameras
### 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)
-
-
- Captured with 8 consumer cameras +
+ Novel view synthesis for chanllenge motion(coming soon)
-
- Novel view synthesis for chanllenge motion(coming soon) +
+ Novel view synthesis for human interaction(coming soon)
@@ -97,12 +102,12 @@ If you would like to download the ZJU-Mocap dataset, please sign the [agreement]

- LightStage: captured with LightStage system + LightStage: captured with LightStage system

- Mirrored-Human: collected from the Internet + Mirrored-Human: collected from the Internet
## Other features @@ -127,7 +132,7 @@ If you would like to download the ZJU-Mocap dataset, please sign the [agreement]
- Calibration for intrinsic and extrinsic parameters + Calibration for intrinsic and extrinsic parameters ### [Annotator](apps/annotation/Readme.md) @@ -136,7 +141,7 @@ If you would like to download the ZJU-Mocap dataset, please sign the [agreement]
- Annotator for bounding box, keypoints and mask + Annotator for bounding box, keypoints and mask ### Other @@ -232,4 +237,4 @@ Please consider citing these works if you find this repo is useful for your proj [^bochkovskiy2020]: Bochkovskiy, Alexey, Chien-Yao Wang, and Hong-Yuan Mark Liao. "Yolov4: Optimal speed and accuracy of object detection." arXiv preprint arXiv:2004.10934 (2020). - +[^hrnet] Sun, Ke, et al. "Deep high-resolution representation learning for human pose estimation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019.