---
license: cc
language:
- en
base_model:
- heyleandro/DINOcular
---
## Overview

Model weights and inference code for DINOcular - a self-supervised RGB-D encoder that learns joint visuospatial representations from RGB-D observations.

[project page](https://heyleadro.github.io/dinocular-project/) , [arxiv](https://arxiv.org/abs/2608.27226) 

## Input
  - `rgb`: image tensor of shape `(B, 3, H, W)`, normalized with ImageNet stats
  - `depth`: depth map tensor of shape `(B, 1, H, W)` (same spatial size as the image), raw metric depth (i.e. in meters)

## Requirements

```
torch
timm
```

## Usage

```python
import torch
from DINOcular import DINOcular_S

chkpt = torch.load("dinocular_s.pth", map_location="cpu", weights_only=False)
model = DINOcular_S()
model.load_state_dict(chkpt, strict=False)
model.eval()

rgb   = torch.randn(1, 3, 224, 224)   # IMAGENET normalized RGB image
depth = torch.randn(1, 1, 224, 224)   # raw metric depth (in meters) 

with torch.no_grad():
    features = model(rgb, depth) # output features
```