assets

README.md

@@ -2,7 +2,7 @@
 
 The official implementation of work "Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models".
 
-#### [[Project Page]](https://vita-group.github.io/Diffusion4D/) | [[Video (Youtube)]](https://www.youtube.com/watch?v=XJT-cMt_xVo) | [[Video (results)]](https://www.youtube.com/watch?v=sg7uUUfpM-c) | [[视频 (Bilibili)]](https://b23.tv/ojVe6Uv) | [[Arxiv]](https://arxiv.org/abs/2405.16645) | [[Dataset]](https://huggingface.co/datasets/hw-liang/Diffusion4D)
+[[Project Page]](https://vita-group.github.io/Diffusion4D/) | [[Arxiv]](https://arxiv.org/abs/2405.16645) | [[Video (Youtube)]](https://www.youtube.com/watch?v=XJT-cMt_xVo) | [[Video (results)]](https://www.youtube.com/watch?v=sg7uUUfpM-c) | [[视频 (Bilibili)]](https://b23.tv/ojVe6Uv) | [[Arxiv]](https://arxiv.org/abs/2405.16645) | [[Huggingface Dataset]](https://huggingface.co/datasets/hw-liang/Diffusion4D)
 
 ## News
 - 2024.6.4:  Released rendered data from curated [objaverse-1.0](https://huggingface.co/datasets/hw-liang/Diffusion4D/tree/main/objaverse1.0_curated), including orbital videos of dynamic 3D, orbital videos of static 3D, and monocular videos from front view.
@@ -11,7 +11,7 @@ The official implementation of work "Diffusion4D: Fast Spatial-temporal Consiste
 
 
 
-# 4D Dataset Preparation
+## 4D Dataset Preparation
 ![dataset_video](./assets/dataset_web.gif)
 
 We collect a large-scale, high-quality dynamic 3D(4D) dataset sourced from the
@@ -20,7 +20,7 @@ vast 3D data corpus of [Objaverse-1.0](https://objaverse.allenai.org/objaverse-1
 2. A render script using Blender, providing optional settings to render your personalized data.
 3. [Rendered 4D images](https://huggingface.co/datasets/hw-liang/Diffusion4D/tree/main/objaverse1.0_curated) by our team to save you GPU time. 
 
-## 4D Dataset ID/Metadata
+### 4D Dataset ID/Metadata
 We first collect 365k dynamic 3D assets from Objaverse-1.0 (42k) and Objaverse-xl (323k). Then we curate a high-quality subset to train our models. 
 
 With objaverse-1.0, we provide the selected 11k ids in `rendering/src/ObjV1_curated.txt`. The uncurated 42k IDs of all the animated objects from objaverse-1.0 are in `rendering/src/ObjV1_all_animated.txt`.
@@ -30,7 +30,7 @@ Metadata of animated objects (323k) from objaverse-xl can be found in [huggingfa
 For text-to-4D generation, the captions are obtained from the work [Cap3D](https://huggingface.co/datasets/tiange/Cap3D). 
 More about the dataset and curation scripts are coming soon!
 
-## 4D Dataset Rendering Script
+### 4D Dataset Rendering Script
 1. Clone the repository and enter the rendering directory:
 
 ```bash
@@ -111,9 +111,9 @@ Output Explanation:
 Our rendering script is based on [point-e](https://github.com/openai/point-e/blob/main/point_e/evals/scripts/blender_script.py) and [Objaverse](https://github.com/allenai/objaverse-xl/blob/main/scripts/rendering/blender_script.py) rendering scripts. Thanks a lot to all the authors for sharing!
 
 
-# Other codes will be released soon!
+## Other codes will be released soon!
 
-# Acknowledgement
+### Acknowledgement
 This project is based on numerous outstanding research efforts and open-source contributions. We are deeply grateful to all the authors for their generosity in sharing their work!
 - https://github.com/alibaba/VideoMV
 - https://github.com/hustvl/4DGaussians
@@ -124,7 +124,7 @@ This project is based on numerous outstanding research efforts and open-source c
 - https://github.com/crockwell/Cap3D
 - https://github.com/openai/point-e
 
-## If you find this repository/work/dataset helpful in your research, please consider citing the paper and starring the repo ⭐.
+### If you find this repository/work/dataset helpful in your research, please consider citing the paper and starring the repo ⭐.
 
 ```
 @article{liang2024diffusion4d,