Views
No views yet
| Format | File | Use Case |
|---|---|---|
| PyTorch (.pth) | pytorch/freya_v1.pth | Training, fine-tuning |
| SafeTensors | pytorch/freya_v1.safetensors | Fast loading, safe |
| ONNX | onnx/freya_depth_v1.onnx | Cross-platform depth inference |
| TensorRT FP16 | tensorrt/freya_depth_v1_fp16.engine | Edge deployment (Jetson/L4) |
| TensorRT FP32 | tensorrt/freya_depth_v1_fp32.engine | Full precision inference |
| Checkpoint | checkpoints/best.pth | Resume SLAM optimization |
| Config | configs/training.toml | Reproducibility |
| Logs | logs/training_history.json | Loss curves, metrics |
| Parameter | Value |
|---|---|
| Hardware | NVIDIA L4 (23GB VRAM) |
| Dataset | TUM VI Benchmark (room1, 2821 frames) |
| Gaussians | 12.2M pre-allocated, 500K active |
| Optimizer | Adam (per-param, foreach=False) |
| Mixed Precision | bf16 |
| Best Loss | 0.0010 |
| VRAM Usage | 17.8GB (77%) |
1import torch
2
3state = torch.load("pytorch/freya_v1.pth", weights_only=False)
4gaussian_map = state["gaussian_map"]
5trajectory = state["trajectory"]
6
7# SafeTensors
8from safetensors.torch import load_file
9tensors = load_file("pytorch/freya_v1.safetensors")1@article{lang2025gaussianlic2,
2 title={Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM},
3 author={Lang, Xiaolei and Lv, Jiajun and Tang, Kai and Li, Laijian and Huang, Jianxin and Liu, Lina and Liu, Yong and Zuo, Xingxing},
4 year={2025},
5 journal={arXiv preprint arXiv:2507.04004}
6}