Downloads · 30 days
0
project_huginn
ilessio-aiflowlab/project_huginn
project_huginn is a robotics model from ilessio-aiflowlab. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as apache-2.0.
Part of the ANIMA Perception Suite by Robot Flow Labs.
Access
Public
Updated Apr 2, 2026
Repo size
4.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth4.4 GB · 100%
At a glance
- Task
- Robotics
- Library
- pytorch
- License
- apache-2.0
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Apr 2, 2026
- SHA
- 3d887a60
Model card
From the Hugging Face model README
HUGINN — OMG4 Optimized Minimal 4D Gaussian Splatting
Part of the ANIMA Perception Suite by Robot Flow Labs.
Paper
OMG4: Optimized Minimal 4D Gaussian Splatting (Oct 2025) Minseo Lee, Byeonghyeon Lee, Lucas Yunkyu Lee, Eunsoo Lee, Sangmin Kim, Seunghyeon Song, Joo Chan Lee, Jong Hwan Ko, et al. Paper | Project Page
Architecture
Three-stage progressive pruning pipeline for compact dynamic 3D scenes:
- Gaussian Sampling — Importance-based retention (opacity x spatial variance x temporal variance)
- Gaussian Pruning — Opacity thresholding + spatial overlap removal
- Gaussian Merging — Weighted fusion of similar primitives
- SVQ Compression — Sub-Vector Quantization with multi-codebook encoding (20.7x compression)
Renderer: gsplat 1.5.3 CUDA kernels (563 FPS @ 50K Gaussians, 800x800)
D-NeRF Benchmark Results
| Scene | Test PSNR | Test SSIM | Gaussians (post-prune) |
|---|---|---|---|
| hellwarrior | 27.49 dB | 0.838 | 7,944 |
| mutant | 23.29 dB | 0.910 | ~100 |
| standup | 21.11 dB | 0.921 | ~40K |
| trex | 20.90 dB | 0.924 | ~3K |
| jumpingjacks | 19.93 dB | 0.920 | ~16K |
| hook | 19.71 dB | 0.858 | 19,182 |
| bouncingballs | 19.54 dB | 0.743 | ~1K |
| lego | 14.67 dB | 0.540 | ~88K |
Primary model: hellwarrior (best quality, 27.49 dB -- near paper target of 28 dB)
Exported Formats
| Format | File | Size | Use Case |
|---|---|---|---|
| PyTorch (.pth) | pytorch/huginn_v3.pth | 1.9 MB | Training, fine-tuning |
| SafeTensors | pytorch/huginn_v3.safetensors | 1.9 MB | Fast loading, safe |
| ONNX (projection) | onnx/huginn_projection_v3.onnx | <1 MB | Cross-platform inference |
| ONNX (SVQ decoder) | onnx/huginn_decoder_v3.onnx | <1 MB | Compressed inference |
| TensorRT FP16 | tensorrt/huginn_projection_v3_fp16.trt | 0.5 MB | Edge (Jetson/L4) |
| TensorRT FP32 | tensorrt/huginn_projection_v3_fp32.trt | 0.5 MB | Full precision |
| Per-scene checkpoints | scenes/{scene}_best.pth | varies | Scene-specific models |
Usage
import torch
from safetensors.torch import load_file
# Load Gaussian attributes
state = load_file("pytorch/huginn_v3.safetensors")
means = state["means"] # (N, 3)
quats = state["quats"] # (N, 4) -- rotation quaternions
scales = state["scales"] # (N, 3) -- scale factors
sh_coeffs = state["sh_coeffs"] # (N, 16, 3) -- SH appearance
opacities = state["opacities"] # (N,)
# Render with gsplat
import gsplat
render_colors, render_alphas, info = gsplat.rasterization(
means=means, quats=quats, scales=scales,
opacities=opacities, colors=sh_coeffs,
viewmats=viewmat, Ks=K, width=800, height=800, sh_degree=3,
)
Training
- Hardware: NVIDIA L4 (23GB VRAM) x 1 GPU
- Framework: PyTorch 2.10 + CUDA 12.8 + gsplat 1.5.3
- Dataset: D-NeRF (8 dynamic scenes, 800x800 native resolution)
- Gaussians: 3M initial, pruned per scene
- Iterations: 30K per scene
- Parallel: 4 scenes simultaneously on 1 GPU
- Total time: ~6 hours for all 8 scenes
- Config: See
configs/train_l4_max.yaml
SVQ Compression
Sub-Vector Quantization achieves 20.7x compression (4.8% of original size):
- Position codebook: 256 entries
- Covariance codebook: 256 entries
- Appearance codebook: 256 entries
- Opacity+time codebook: 256 entries
License
Apache 2.0 -- Robot Flow Labs / AIFLOW LABS LIMITED
Built with ANIMA by Robot Flow Labs
- Task
- Robotics
- Library
- pytorch
- License
- apache-2.0
- Created
- Mar 28, 2026
- Updated
- Apr 2, 2026