---
tags:
  - robotics
  - anima
  - urd
  - uniscale
  - 3d-reconstruction
  - depth-estimation
  - multi-view
  - robot-flow-labs
library_name: pytorch
pipeline_tag: depth-estimation
license: apache-2.0
---

# URD — UniScale Unified Scale-Aware Multi-View 3D Reconstruction

Part of the [ANIMA Perception Suite](https://github.com/RobotFlow-Labs) by Robot Flow Labs.

## Paper

**UniScale: Unified Scale-Aware Multi-View 3D Reconstruction**
arXiv: [2602.23224](https://arxiv.org/abs/2602.23224)

## Architecture

UniScale combines camera intrinsics, extrinsics, metric depth, and 3D point cloud generation into a single neural network forward pass. The core design leverages frozen DINOv2 ViT-B/14 foundation model features with lightweight scale-aware pose and depth decoders, enabling metrically consistent multi-view 3D reconstruction without iterative optimization (no RANSAC, no bundle adjustment).

Key components:
- **Foundation Encoder**: Frozen DINOv2 ViT-B/14 (86M params)
- **Scale-Aware Pose Decoder**: Estimates intrinsics + extrinsics + metric scale
- **Metric Depth Generator**: Dense depth maps with confidence estimation
- **Point Cloud Generator**: Direct 3D point maps in metric world coordinates

## Exported Formats

| Format | File | Size | Use Case |
|--------|------|------|----------|
| PyTorch (.pth) | `pytorch/urd_v1.pth` | ~1.0 GB | Training, fine-tuning, resume |
| SafeTensors | `pytorch/urd_v1.safetensors` | ~347 MB | Fast loading, safe deserialization |
| ONNX | `onnx/urd_v1.onnx` | ~347 MB | Cross-platform inference |
| TensorRT FP16 | `tensorrt/urd_v1_fp16.engine` | ~177 MB | Edge deployment (Jetson/L4) |
| TensorRT FP32 | `tensorrt/urd_v1_fp32.engine` | ~355 MB | Full precision inference |

## Training

- **Dataset**: NYU Depth V2 (654 train / 654 val)
- **Hardware**: NVIDIA L4 (23GB VRAM)
- **Checkpoint**: `final.pth` (epoch 30/30)
- **Stages**: 2-stage curriculum
  - Stage 1 (epochs 1-5): Frozen encoder, batch=64, lr=1e-4
  - Stage 2 (epochs 6-30): Unfrozen encoder, batch=16, lr=1e-5, gradient checkpointing
- **Best val_loss**: 0.1175 (epoch 18)
- **Training time**: ~97 minutes
- **Optimizer**: AdamW (weight_decay=0.01)
- **Scheduler**: Cosine annealing with 2-epoch warmup
- **Seed**: 42

See `configs/` for full hyperparameters and `logs/training_history.json` for loss curves.

## Usage

```python
import torch
from anima_urd.model import UniScale

# Load from checkpoint
model = UniScale.load("pytorch/urd_v1.pth", device="cuda")
model.eval()

# Inference: 4 multi-view images at 512x512
images = torch.randn(1, 4, 3, 512, 512, device="cuda")
with torch.no_grad():
    output = model(images)
    depth = output.depth_maps           # [1, 4, 512, 512] metric depth (meters)
    confidence = output.depth_confidence # [1, 4, 512, 512]
    intrinsics = output.intrinsics      # [1, 3, 3]
    scale = output.scale_factors        # [1] metric scale
```

## Multi-Robot Deployment

UniScale is designed for multi-robot coordination:
- Each robot runs feed-forward inference locally (no iterative optimization)
- Predicted metric scale enables direct point cloud merging across robots
- Linear scaling O(N*M) vs quadratic O(N^2*M^2) for traditional BA

## Citation

```bibtex
@article{UniScale_2026,
  title={UniScale Unified Scale-Aware Multi-View 3D Reconstruction},
  year={2026},
  eprint={2602.23224},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2602.23224}
}
```

## License

Apache 2.0 — Robot Flow Labs / AIFLOW LABS LIMITED