Add model card and metadata

README.md

@@ -1,3 +1,33 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: image-to-3d
+---
+
+# PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting
+
+PLANA3R is an end-to-end transformer-based model for two-view metric 3D reconstruction and metric relative pose estimation, specifically designed for structured indoor scenes. It represents scenes using sparse 3D planar primitives.
+
+- **Paper:** [PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting](https://huggingface.co/papers/2510.18714)
+- **Project Page:** [https://lck666666.github.io/plana3r/](https://lck666666.github.io/plana3r/)
+- **Repository:** [https://github.com/lck666666/plana3r](https://github.com/lck666666/plana3r)
+
+## Introduction
+PLANA3R addresses metric 3D reconstruction of indoor scenes by exploiting their inherent geometric regularities with compact representations. Using planar 3D primitives—a well-suited representation for man-made environments—it introduces a pose-free framework for metric Planar 3D Reconstruction from unposed two-view images. Unlike prior feedforward methods that require 3D plane annotations during training, PLANA3R learns planar 3D structures without explicit plane supervision, enabling scalable training on large-scale datasets.
+
+## Key Features
+- **Zero-shot Generalization**: Demonstrates strong generalization to out-of-domain indoor environments.
+- **Metric 3D Reconstruction**: Provides accurate metric measurements for indoor scenes.
+- **Planar Representation**: Efficiently represents man-made environments using sparse 3D planar primitives.
+- **Emergent Segmentation**: Formulated with planar representations, the method naturally enables accurate plane segmentation.
+
+## Citation
+```bibtex
+@inproceedings{
+liu2025plana3r,
+title={PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting},
+author={Changkun Liu and Bin Tan and Zeran Ke and Shangzhan Zhang and Jiachen Liu and Ming Qian and Nan Xue and Yujun Shen and Tristan Braud},
+booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
+year={2025},
+url={https://openreview.net/forum?id=YTwRZP8mNO}
+}
+```