LightStage is a multi-view dataset, which is proposed in NeuralBody. This dataset captures multiple dynamic human videos using a multi-camera system that has 20+ synchronized cameras. The humans perform complex motions, including twirling, Taichi, arm sw
data_root: "data/zju-mocap/my_377" human: "my_377" ann_file: "data/zju-mocap/my_377/annots.npy" split: "test" bullet: dataset_module: "lib.datasets.h36m.tpose_novel_view_dataset" dataset_kwargs: data_root: "data/zju-mocap/my_377" ann_file: "data/zju-mocap/my_377/annots.npy...
05/12/2021 We update the ZJU-MoCap dataset with better fitted SMPL using EasyMocap. We also release a website for visualization. Please see here for the usage of provided smpl parameters.Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic...
We release the interactive rendering GUI for ZJU-MoCap dataset. python gui_human.py --cfg_file configs/enerf/interactive/zjumocap.yaml Usage: Mouse wheel: Zoom in/out Mouse left button: Move Mouse right button: Rotate Keyboard a: Align # Hold down a and then use the mouse right button ...
Note that you can change out the 0013_01 and renbody parts for other names for you custom dataset. Other namings like 4k4d should remain the same. Let's assume a typical input contains calibrated camera parameters compatible with EasyMocap, where the folder & directory structure looks like ...
1. Prepare ZJU-MoCap and NHR datasets. Please refer tomlp_mapsto download ZJU-MoCap and NHR datasets. After downloading, place them into$workspace/zju-mocapand$workspace/NHR, respectively. 2. Prepare the DNA-Rendering dataset. Since the license of theDNA-Renderingdataset does not allow distribut...