---
tags:
  - robotics
  - anima
  - slam
  - gaussian-splatting
  - semantic-slam
  - robot-flow-labs
library_name: pytorch
pipeline_tag: robotics
license: apache-2.0
---

# GS3LAM — Gaussian Semantic Splatting SLAM

Part of the [ANIMA Intelligence Compiler Suite](https://robotflowlabs.com) by Robot Flow Labs.

**Wave 7 | Domain: SLAM | Module: slam-gs3lam**

## Paper

**GS3LAM: Gaussian Semantic Splatting SLAM**
Linfei Li, Lin Zhang, Zhong Wang, Ying Shen
ACM MM 2024 | [arXiv 2603.27781](https://arxiv.org/abs/2603.27781) | [DOI](https://doi.org/10.1145/3664647.3680739)

## Architecture

Dense semantic RGB-D SLAM using a Semantic Gaussian Field (SG-Field). Each Gaussian stores position, covariance, opacity, RGB color, and a 16-dimensional semantic feature vector. A lightweight 1x1 Conv2d decoder maps semantic features to per-pixel class logits.

Core components:
- **SG-Field**: 3D Gaussian representation with semantic features
- **Differentiable Splatting**: CUDA-accelerated rendering via gaussian-semantic-rasterization
- **Tracking**: Frame-to-model pose optimization (rotation + translation)
- **Mapping**: Joint optimization of Gaussians + semantic decoder
- **DSR**: Depth-adaptive Scale Regularization
- **RSKM**: Random Sampling-based Keyframe Mapping

## Exported Formats

| Format | File | Use Case |
|--------|------|----------|
| SafeTensors (field) | `pytorch/gs3lam_office2_v1_field.safetensors` | Gaussian field parameters |
| SafeTensors (decoder) | `pytorch/gs3lam_office2_v1_decoder.safetensors` | Semantic decoder weights |
| ONNX (decoder) | `onnx/gs3lam_office2_v1_decoder.onnx` | Cross-platform decoder inference |
| Poses (npy) | `pytorch/gs3lam_office2_v1_poses.npy` | Estimated camera trajectory [N,4,4] |
| Checkpoint | `checkpoints/best.pt` | Full checkpoint for resuming |

**Note**: TensorRT engines must be generated on target hardware due to architecture-specific compilation.

## Training Details

- **Scene**: Replica office2 (2000 frames, 1200x680 rendered at 600x340)
- **Hardware**: NVIDIA L4 23GB
- **Config**: 20 tracking iterations, 15 mapping iterations (L4-tuned)
- **Gaussians**: 21K (capped at 80K with periodic pruning)
- **Duration**: ~5.5 hours
- **CUDA Extension**: gaussian-semantic-rasterization (sm_89)

### Current Metrics (L4 baseline, reduced resolution)

| Metric | Value | Paper Target |
|--------|-------|-------------|
| PSNR | 3.39 dB | >= 35.0 dB |
| ATE | 178 cm | <= 0.50 cm |

> **Note**: These metrics reflect an L4-constrained run at half resolution with aggressive Gaussian capping (21K vs paper's ~775K). Paper-quality reproduction requires full resolution on A100/H100 hardware.

## Usage

```python
import torch
from anima_slam_gs3lam.export import load_checkpoint, reconstruct_field, reconstruct_decoder

ckpt = load_checkpoint("checkpoints/best.pt")
field = reconstruct_field(ckpt, device="cuda")
decoder = reconstruct_decoder(ckpt, device="cuda")
```

## API

```bash
# Start service
python -m anima_slam_gs3lam

# Health check
curl http://localhost:8080/health
curl http://localhost:8080/ready
curl http://localhost:8080/info
```

## Docker

```bash
docker compose -f docker-compose.serve.yml --profile api up -d
```

## CUDA Extension

The gaussian-semantic-rasterization CUDA kernel is shared at:
`/mnt/forge-data/shared_infra/cuda_extensions/gaussian_semantic_rasterization/`

## License

Apache 2.0 — Robot Flow Labs / AIFLOW LABS LIMITED