Downloads · 30 days
0
project_def_rpga
ilessio-aiflowlab/project_def_rpga
project_def_rpga 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 Intelligence Compiler Suite by Robot Flow Labs.
Access
Public
Updated Apr 3, 2026
Repo size
747 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth496 MB · 66%
At a glance
- Task
- Robotics
- Library
- pytorch
- License
- apache-2.0
- Access
- Public
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026
- SHA
- 5c48f73a
Model card
From the Hugging Face model README
DEF-RPGA — Adversarial Camouflage via 3D Gaussian Splatting
Part of the ANIMA Intelligence Compiler Suite by Robot Flow Labs.
Paper
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation arXiv: 2507.01367
Authors: Tianrui Lou, Xiaojun Jia, Siyuan Liang, Jiawei Liang, Ming Zhang, Yanjun Xiao, Xiaochun Cao
Architecture
DEF-RPGA uses 3D Gaussian Splatting as a differentiable attack substrate for generating multi-view robust physical adversarial camouflage. The pipeline:
- Scene Representation: 3DGS point cloud with SH coefficients
- Attack Target: Optimize only zero-order SH (SH0) color terms
- Differentiable Rendering: CUDA rasterizer (
diff-gaussian-rasterization) - Adversarial Objective: Suppress detector confidence (paper Eq. 6)
- Regularization: Cross-view consistency, NPS (Non-Printability Score), primary-color regularization
- Background Hardening: Min-max perturbation to filter non-robust features (paper Eq. 9)
Exported Formats
| Format | File | Use Case |
|---|---|---|
| PyTorch (.pth) | pytorch/def_rpga_v1.pth | Training, fine-tuning |
| SafeTensors | pytorch/def_rpga_v1.safetensors | Fast loading, safe |
| ONNX | onnx/def_rpga_v1.onnx | Cross-platform inference |
| TensorRT FP16 | tensorrt/def_rpga_v1_fp16.trt | Edge deployment (Jetson/L4) |
| TensorRT FP32 | tensorrt/def_rpga_v1_fp32.trt | Full precision inference |
Usage
import torch
from anima_def_rpga.scene.gaussian_state import GaussianState
from anima_def_rpga.scene.checkpoint_loader import load_gaussian_state
# Load trained adversarial camouflage
state = load_gaussian_state("pytorch/def_rpga_v1.pth")
print(f"Gaussians: {state.gaussian_count}, SH0 shape: {state.sh0.shape}")
# The SH0 values encode the adversarial color pattern
adversarial_colors = torch.sigmoid(state.sh0) # [N, 3] RGB
Training
- Hardware: NVIDIA L4 (23 GB VRAM)
- Framework: PyTorch 2.11 + CUDA 12.8
- Rasterizer: diff-gaussian-rasterization (CUDA kernel)
- Optimizer: Adam (fused), lr=0.01, warmup + cosine decay
- Batch size: 80 views per step (67.1% VRAM utilization)
- Scene: 1M Gaussians
- Resolution: 480×640
- Steps: 20,000
- Config: See
configs/train_cuda.toml
Evaluation Targets (Paper §5)
| Benchmark | Metric | Paper Value | Our Target |
|---|---|---|---|
| Digital white-box angle sweep | [email protected] on Faster R-CNN | 6.73 | ≤ 8.0 |
| Hardest angle (60°) | [email protected] | 0.00 | ≤ 2.0 |
| 1:1 real car | [email protected] | 25.67 | ≤ 30.0 |
ANIMA Module
- Codename: DEF-RPGA
- Domain: Defense
- Wave: 7
- API: FastAPI at port 8407
- ROS2: Capture + bridge nodes for robotics integration
- Docker:
docker compose -f docker-compose.serve.yml --profile serve up -d
License
Apache 2.0 — Robot Flow Labs / AIFLOW LABS LIMITED
- Task
- Robotics
- Library
- pytorch
- License
- apache-2.0
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026