---
library_name: pytorch
tags:
  - 3d-segmentation
  - point-cloud
  - interactive-segmentation
  - promptable-segmentation
  - safetensors
---

# DynamicSAM

Interactive 3D point cloud segmentation with adaptive masking. Given a point cloud and click prompts (foreground/background), DynamicSAM produces a per-point foreground probability mask.

- **Input:** XYZ-only point cloud (no RGB) + click prompts (point coordinates + foreground/background labels)
- **Output:** per-point foreground probability, binarized at inference time by a tunable threshold
- **Architecture:** PointBERT-style point cloud encoder, a prompt encoder that shares its positional-embedding MLP with the point cloud encoder, and a two-way-transformer mask decoder with a PointNet++ upsampling head (adapted from the Segment Anything Model's decoder design, without an IoU-prediction head)

## Files

- `model.safetensors` — inference weights (point cloud encoder, prompt encoder, mask decoder), including `group_size`/`num_group` in its metadata.

## Training

- **Dataset:** ScanNet (ScanNet40)
- **Config:** `trans_dim=384`, `group_size=32`, `num_group=128`, batch size 128, AdamW + multi-step LR decay

## Usage

Install [dynamic-sam](https://github.com/DESRLab/dynamic-sam.git) with the `inference` extra, then serve directly from this repo:

```bash
pip install -e ".[inference]"
dynamic-sam serve --hf-repo-id Marali/dynamic-sam
```

This downloads `model.safetensors` through the local Hugging Face cache (`HF_HOME`) and serves it behind a FastAPI HTTP API (`/encode_pcd`, `/predict_mask`).

To load the weights directly in Python instead:

```python
from src.serve.checkpoint import load_dynamic_sam

model = load_dynamic_sam("model.safetensors", device=0)
```