first

.gitignore

@@ -0,0 +1 @@
+rendering/blender-3.2.2-linux-x64

README.md

@@ -1 +1,38 @@
 # Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
+Authors: Hanwen Liang*, Yuyang Yin*, Dejia Xu, Hanxue Liang, Zhangyang Wang, Konstantinos N. Plataniotis, Yao Zhao, Yunchao Wei (*Equal contribution)
+
+Instituions: University of Toronto, Beijing Jiaotong University, University of Texas at Austin, University of Cambridge
+
+
+# Preparation of 4D data
+We curate a large-scale, high-quality dynamic 3D(4D) dataset sourced from the
+vast 3D data corpus of [Objaverse-1.0](https://objaverse.allenai.org/objaverse-1.0/) and [Objaverse-XL](https://github.com/allenai/objaverse-xl). We apply a series of empirical rules to filter the dataset. You can find more details in our paper. In this part, we release the selected 4D assets including:
+1. Selected high-quality 4D object ID.
+2. A render script using Blender, providing optional settings to render your personalized data.
+3. (To be uploaded) Rendered 4D images by our team to save you GPU time.
+
+## 4D Dataset ID
+介绍下下总体统计情况，id的链接 @dejia @hanwen
+
+## 4D Dataset Rendering Script
+1. Clone the repository and enter the rendering directory:
+
+```bash
+git clone https://github.com/Ir1d/Diffusion4D.git && \
+cd rendering
+```
+
+2. Download Blender:
+```bash
+wget https://download.blender.org/release/Blender3.2/blender-3.2.2-linux-x64.tar.xz && \
+tar -xf blender-3.2.2-linux-x64.tar.xz && \
+rm blender-3.2.2-linux-x64.tar.xz
+```
+
+3. Download 4D objects
+```bash
+python download.py --id_path test.txt
+```
+
+
+4. Render 4D images