Update model card: add pipeline tag, paper and code links

README.md

@@ -1,12 +1,21 @@
 ---
-license: bsd-3-clause
 language:
 - en
+license: bsd-3-clause
 tags:
 - scene-flow
 - point-cloud
 - codebase
 - 3d-vision
+pipeline_tag: robotics
+---
+
+# DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method
+
+This repository contains the model weights for **DeltaFlow**, presented in the paper [DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method](https://huggingface.co/papers/2508.17054).
+
+The code is open-sourced along with trained model weights at the official GitHub repository: [https://github.com/Kin-Zhang/DeltaFlow](https://github.com/Kin-Zhang/DeltaFlow).
+
 ---
 
 <p align="center">
@@ -19,8 +28,8 @@ tags:
 
 💞 If you find [*OpenSceneFlow*](https://github.com/KTH-RPL/OpenSceneFlow) useful to your research, please cite [**our works** 📖](#cite-us) and give [a star 🌟](https://github.com/KTH-RPL/OpenSceneFlow) as encouragement. (੭ˊ꒳​ˋ)੭✧
 
-[*OpenSceneFlow*](https://github.com/KTH-RPL/OpenSceneFlow) is a codebase for point cloud scene flow estimation. 
-Please check the usage on [KTH-RPL/OpenSceneFlow](https://github.com/KTH-RPL/OpenSceneFlow). 
+[*OpenSceneFlow*](https://github.com/KTH-RPL/OpenSceneFlow) is a codebase for point cloud scene flow estimation.
+Please check the usage on [KTH-RPL/OpenSceneFlow](https://github.com/KTH-RPL/OpenSceneFlow).
 Here we upload our demo data and checkpoint for the community.
 
 ## 🎁 One repository, All methods!
@@ -37,7 +46,7 @@ Officially:
 - [x] [DeFlow](https://arxiv.org/abs/2401.16122) (Ours 🚀): ICRA 2024
 
 <details> <summary> Reoriginse to our codebase:</summary>
-  
+
 - [x] [FastFlow3d](https://arxiv.org/abs/2103.01306): RA-L 2021
 - [x] [ZeroFlow](https://arxiv.org/abs/2305.10424): ICLR 2024, their pre-trained weight can covert into our format easily through [the script](https://github.com/KTH-RPL/OpenSceneFlow/tools/zerof2ours.py).
 - [x] [NSFP](https://arxiv.org/abs/2111.01253): NeurIPS 2021, faster 3x than original version because of [our CUDA speed up](https://github.com/KTH-RPL/OpenSceneFlow/assets/cuda/README.md), same (slightly better) performance. Done coding, public after review.
@@ -49,13 +58,13 @@ Officially:
 
 ## Notes
 
-The tree of uploaded files: 
+The tree of uploaded files:
 * [ModelName_best].ckpt: means the model evaluated in the public leaderboard page provided by authors or our retrained with the best parameters.
 * [demo-data-v2.zip](https://huggingface.co/kin-zhang/OpenSceneFlow/blob/main/demo_data.zip): 1.2GB, a mini-dataset for user to quickly run train/val code. Check usage in [this section](https://github.com/KTH-RPL/SeFlow?tab=readme-ov-file#1-run--train).
 * [waymo_map.tar.gz](https://huggingface.co/kin-zhang/OpenSceneFlow/blob/main/waymo_map.tar.gz): to successfully process waymo data with ground segmentation included to unified h5 file. Check usage in [this README](https://github.com/KTH-RPL/SeFlow/blob/main/dataprocess/README.md#waymo-dataset).
 * [demo_data.zip](https://huggingface.co/kin-zhang/OpenSceneFlow/blob/main/demo_data.zip): 1st version (will deprecated later) 613Mb, a mini-dataset for user to quickly run train/val code. Check usage in [this section](https://github.com/KTH-RPL/OpenSceneFlow?tab=readme-ov-file#1-run--train).
 
-All test result reports can be found [v2 leaderboard](https://github.com/KTH-RPL/DeFlow/discussions/6) 
+All test result reports can be found [v2 leaderboard](https://github.com/KTH-RPL/DeFlow/discussions/6)
 and [v1 leaderboard](https://github.com/KTH-RPL/DeFlow/discussions/2).
 
 ## Cite Us
@@ -74,8 +83,8 @@ and [v1 leaderboard](https://github.com/KTH-RPL/DeFlow/discussions/2).
 }
 @inproceedings{zhang2024deflow,
   author={Zhang, Qingwen and Yang, Yi and Fang, Heng and Geng, Ruoyu and Jensfelt, Patric},
-  booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA)}, 
-  title={{DeFlow}: Decoder of Scene Flow Network in Autonomous Driving}, 
+  booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA)},
+  title={{DeFlow}: Decoder of Scene Flow Network in Autonomous Driving},
   year={2024},
   pages={2105-2111},
   doi={10.1109/ICRA57147.2024.10610278}
@@ -105,8 +114,8 @@ And our excellent collaborators works as followings:
 }
 @article{kim2025flow4d,
   author={Kim, Jaeyeul and Woo, Jungwan and Shin, Ukcheol and Oh, Jean and Im, Sunghoon},
-  journal={IEEE Robotics and Automation Letters}, 
-  title={Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation}, 
+  journal={IEEE Robotics and Automation Letters},
+  title={Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation},
   year={2025},
   volume={10},
   number={4},