metadata
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:
For more details, visit the project page and code repository:
- Project Page: https://aigeeksgroup.github.io/3D-R1
- Code: https://github.com/AIGeeksGroup/3D-R1