Downloads · 30 days
0
PonderV2
HaoyiZhu/PonderV2
PonderV2 is a image feature extraction model from HaoyiZhu. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Access
Public
Updated Sep 30, 2025
Repo size
2.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth2.1 GB · 100%
At a glance
- Task
- Image Feature Extraction
- License
- mit
- Access
- Public
- Created
- Sep 30, 2025
- Updated
- Sep 30, 2025
- SHA
- 09eab60b
Model card
From the Hugging Face model README
<div align='center'>
<h2>PonderV2: Pave the Way for 3D Foundation Model <br>with A Universal Pre-training Paradigm</h2>
Haoyi Zhu<sup>1,4*</sup>, Honghui Yang<sup>1,3*</sup>, Xiaoyang Wu<sup>1,2*</sup>, Di Huang<sup>1*</sup>, Sha Zhang<sup>1,4</sup>, Xianglong He<sup>1</sup>, <br> Hengshuang Zhao<sup>2</sup>, Chunhua Shen<sup>3</sup>, Yu Qiao<sup>1</sup>, Tong He<sup>1</sup>, Wanli Ouyang<sup>1</sup>
<sup>1</sup>Shanghai AI Lab, <sup>2</sup>HKU, <sup>3</sup>ZJU, <sup>4</sup>USTC
</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 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>- Task
- Image Feature Extraction
- License
- mit
- Languages
- en
- Created
- Sep 30, 2025
- Updated
- Sep 30, 2025