|
|
--- |
|
|
pipeline_tag: image-text-to-text |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding |
|
|
|
|
|
**3D-R1** is a foundation model designed to enhance the reasoning capabilities of 3D Vision-Language Models (VLMs) for unified scene understanding. It addresses limitations in existing 3D VLMs by leveraging a high-quality synthetic dataset (Scene-30K), incorporating RLHF policies with novel reward functions (perception, semantic similarity, format), and introducing a dynamic view selection strategy. This approach aims to improve robust reasoning and generalization in 3D scene understanding. |
|
|
|
|
|
The model was presented in the paper: |
|
|
- **Paper**: [3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding](https://huggingface.co/papers/2507.23478) |
|
|
|
|
|
For more details, visit the project page and code repository: |
|
|
- **Project Page**: [https://aigeeksgroup.github.io/3D-R1](https://aigeeksgroup.github.io/3D-R1) |
|
|
- **Code**: [https://github.com/AIGeeksGroup/3D-R1](https://github.com/AIGeeksGroup/3D-R1) |
