The Overwatch Depth Dataset contains pixel-aligned RGB images and dense depth maps captured from diverse synthetic outdoor environments. Streets, buildings, vegetation, open spaces, and long-range sky regions provide varied geometry for training and evaluating monocular depth estimation models.
- Paired RGB and depth images are provided at a preview resolution of 1024 × 576.
- Depth is stored as an 8-bit grayscale image: black represents nearer geometry and white represents farther geometry within the capture range.
- The displayed depth is normalized rather than expressed directly in meters. Spectral color is used only for visualization and does not change the depth values.
- Five environments form the training split, while Midtown is reserved for testing.
