ModelListedExternal

LaSSM

This repository contains the weights for LaSSM, a framework for efficient 3D scene instance segmentation from point clouds.

Sourcehuggingface.co/RayYoh/LaSSM/tree/be52768d2aebc4ab6a84109111a36d4c8d92369b

KindOtherVersionRevision be52768

Model source

Kind: Other
File size: 210–520 MB
Version: vRevision be52768
Updated: Sep 27, 2026
Downloads: 0
Tasks: Image segmentation
Source: Hugging Face

Source description

LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation

This repository contains the weights for LaSSM, a framework for efficient 3D scene instance segmentation from point clouds.

Description

LaSSM (Local Aggregation and State Space Models) prioritizes simplicity and efficiency in 3D instance segmentation. It introduces a hierarchical semantic-spatial query initializer and a coordinate-guided state space model (SSM) decoder. This design restricts the model to focus on geometrically coherent regions and uses a spatial dual-path SSM block to capture underlying dependencies within the query set, reducing redundant computation.

LaSSM ranks first on the ScanNet++ V2 leaderboard, outperforming previous state-of-the-art methods with significantly fewer FLOPs.

Trained Results

Model	Benchmark	Num GPUs	mAP	AP50	AP25	Config	Tensorboard	Exp Record	Model
LaSSM	ScanNet++ V2 Val	4	29.1	43.5	51.6	Link	Link	Link	Link
LaSSM	ScanNet Val	4	58.4	78.1	86.1	Link	-	Link	Link
LaSSM	ScanNet200 Val	4	29.3	39.2	44.5	Link	-	Link	Link

Citation

@article{yao2025lassm,
  title={LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation},
  author={Yao, Lei and Wang, Yi and Yawen, Cui and Liu, Moyun and Chau, Lap-Pui},
  journal={arXiv preprint arXiv:2602.11007},
  year={2026}
}

Sources

1 source

Hugging FacePrimaryVersion be52768d2aebc4ab6a84109111a36d4c8d92369b

huggingface.co/RayYoh/LaSSM/tree/be52768d2aebc4ab6a84109111a36d4c8d92369b

Verified Sep 27

Model artifacts

4 artifacts

scannet-lassm-spunet-v2-3-best/model/model_best.pth

pth · 210 MB · SHA-256 cc8c2d371aae…e318 · Hugging Face

Download

scannet-lassm-spunet-v2-3/model/model_best.pth

pth · 210 MB · SHA-256 38095054b6d0…9449 · Hugging Face

Download

scannet200-lassm-minkunet-3/model/model_best.pth

pth · 520 MB · SHA-256 c33c25964318…f9a4 · Hugging Face

Download

scannetpp-lassm-spunet-v2-3/model/model_best.pth

pth · 211 MB · SHA-256 78c1e975b92a…5037 · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 27huggingface.co/RayYoh/LaSSM

--- license: mit pipeline_tag: image-segmentation --- # LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation This repository contains the weights for **LaSSM**, a framework for efficient 3D scene instance segmentation from point clouds. - **Paper:** [LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation](https://huggingface.co/papers/2602.11007) - **Code:** [GitHub - RayYoh/LaSSM](https://github.com/RayYoh/LaSSM) ## Description LaSSM (Local Aggregation and State Space Models) prioritizes simplicity and efficiency in 3D instance segmentation. It introduces a hierarchical semantic-spatial query initializer and a coordinate-guided state space model (SSM) decoder. This design restricts the model to focus on geometrically coherent regions and uses a spatial dual-path SSM block to capture underlying dependencies within the query set, reducing redundant computation. LaSSM ranks first on the ScanNet++ V2 leaderboard, outperforming previous state-of-the-art methods with significantly fewer FLOPs. ## Trained Results | Model | Benchmark | Num GPUs | mAP | AP50 | AP25 | Config | Tensorboard | Exp Record | Model | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | LaSSM | ScanNet++ V2 Val | 4 | 29.1 | 43.5 | 51.6 | [Link](https://github.com/RayYoh/LaSSM/blob/main/configs/scannetpp/insseg-lassm-spunet-v2-3.py) | [Link](https://huggingface.co/RayYoh/LaSSM/tensorboard) | [Link](https://huggingface.co/RayYoh/LaSSM/raw/main/scannetpp-lassm-spunet-v2-3/train.log) | [Link](https://huggingface.co/RayYoh/LaSSM/blob/main/scannetpp-lassm-spunet-v2-3/model/model_best.pth) | | LaSSM | ScanNet Val | 4 | 58.4 | 78.1 | 86.1 | [Link](https://github.com/RayYoh/LaSSM/blob/main/configs/scannet/insseg-lassm-spunet-v2-3.py) | - | [Link](https://huggingface.co/RayYoh/LaSSM/raw/main/scannet-lassm-spunet-v2-3/train.log) | [Link](https://huggingface.co/RayYoh/LaSSM/blob/main/scannet-lassm-spunet-v2-3/model/model_best.pth) | | LaSSM | ScanNet200 Val | 4 | 29.3 | 39.2 | 44.5 | [Link](https://github.com/RayYoh/LaSSM/blob/main/configs/scannet200/insseg-lassm-minkunet-3.py) | - | [Link](https://huggingface.co/RayYoh/LaSSM/raw/main/scannet200-lassm-minkunet-3/train.log) | [Link](https://huggingface.co/RayYoh/LaSSM/blob/main/...

NoteSep 27huggingface.co/RayYoh/LaSSM

Source context: 0 downloads · 1 likes · Pipeline image-segmentation · Repo RayYoh/LaSSM