Improve model card: Add pipeline tag and abstract

This pull request enhances the model card for ScoreLiDAR by:
- Adding the `pipeline_tag: other` to the metadata, which improves discoverability on the Hugging Face Hub for its specialized 3D LiDAR scene completion task.
- Incorporating the full paper abstract into the content, providing a detailed summary of the model's approach and results directly on the model page.
- Restructuring the content to prominently feature the paper title, its Arxiv link, and the code repository link at the top, followed by the abstract and an updated "Repo Info" section.

README.md

@@ -4,15 +4,15 @@ tags:
 - 3D point clouds
 - reconstruction
 - ply
+pipeline_tag: other
 ---
 
-# **Repo Info**
+# **ScoreLiDAR: Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion**
 
-<!-- Provide a quick summary of what the model is/does. -->
+[📚 Paper](https://arxiv.org/abs/2412.03515) - [💻 Code Repository](https://github.com/happyw1nd/ScoreLiDAR)
 
-This repo stores checkpoints for the paper: 
-
-[**ScoreLiDAR: Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion**](https://arxiv.org/abs/2412.03515)
-
-For more information and detailed usage of the models, please refer to [this repo](https://github.com/happyw1nd/ScoreLiDAR).
+## Abstract
+Diffusion models have been applied to 3D LiDAR scene completion due to their strong training stability and high completion quality. However, the slow sampling speed limits the practical application of diffusion-based scene completion models since autonomous vehicles require an efficient perception of surrounding environments. This paper proposes a novel distillation method tailored for 3D Li- DAR scene completion models, dubbed ScoreLiDAR, which achieves efficient yet high-quality scene completion. Score- LiDAR enables the distilled model to sample in significantly fewer steps after distillation. To improve completion quality, we also introduce a novel Structural Loss, which encourages the distilled model to capture the geometric structure of the 3D LiDAR scene. The loss contains a scene-wise term constraining the holistic structure and a point-wise term constraining the key landmark points and their relative configuration. Extensive experiments demonstrate that ScoreLiDAR significantly accelerates the completion time from 30.55 to 5.37 seconds per frame (>5x) on SemanticKITTI and achieves superior performance compared to state-of-the-art 3D LiDAR scene completion models. Our model and code are publicly available on https: //github.com/happyw1nd/ScoreLiDAR.
 
+## Repo Info
+This repository stores checkpoints for the ScoreLiDAR paper. For more information and detailed usage of the models, please refer to the [official GitHub repository](https://github.com/happyw1nd/ScoreLiDAR).