Create README.md

README.md

@@ -0,0 +1,30 @@
+---
+pipeline_tag: image-feature-extraction
+language:
+- en
+license: mit
+---
+
+<div align='center'>
+
+<h2>PonderV2: Pave the Way for 3D Foundation Model <br>with A Universal Pre-training Paradigm</h2>
+
+[Haoyi Zhu](https://www.haoyizhu.site/)<sup>1,4*</sup>, [Honghui Yang](https://github.com/Nightmare-n)<sup>1,3*</sup>, [Xiaoyang Wu](https://xywu.me/)<sup>1,2*</sup>, [Di Huang](https://github.com/dihuangdh)<sup>1*</sup>, [Sha Zhang](https://github.com/zhangsha1024)<sup>1,4</sup>, [Xianglong He](https://scholar.google.com/citations?hl=zh-CN&user=jKFeol0AAAAJ)<sup>1</sup>,
+<br>
+[Hengshuang Zhao](https://hszhao.github.io/)<sup>2</sup>, [Chunhua Shen](https://cshen.github.io/)<sup>3</sup>, [Yu Qiao](https://mmlab.siat.ac.cn/yuqiao/)<sup>1</sup>, [Tong He](http://tonghe90.github.io/)<sup>1</sup>, [Wanli Ouyang](https://wlouyang.github.io/)<sup>1</sup>
+ 
+<sup>1</sup>[Shanghai AI Lab](https://www.shlab.org.cn/), <sup>2</sup>[HKU](https://www.hku.hk/), <sup>3</sup>[ZJU](https://www.zju.edu.cn/), <sup>4</sup>[USTC](https://en.ustc.edu.cn/) 
+
+</div>
+
+<p align="center">
+    <img src="assets/radar.png" alt="radar" width="500" />
+</p>
+
+This is the official implementation of the T-PAMI 2025 paper "PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm". 
+
+[PonderV2](https://arxiv.org/abs/2310.08586) is a comprehensive 3D pre-training framework designed to facilitate the acquisition of efficient 3D representations, thereby establishing a pathway to 3D foundational models. It is a novel universal paradigm to learn point cloud representations by differentiable neural rendering, serving as a bridge between 3D and 2D worlds. 
+
+<p align="center">
+    <img src="assets/pipeline.png" alt="pipeline" width="800" />
+</p>