Spaces:
Sleeping
Sleeping
| title: Depth Estimation Demo | |
| emoji: 🌖 | |
| colorFrom: gray | |
| colorTo: gray | |
| sdk: gradio | |
| sdk_version: 6.19.0 | |
| python_version: '3.13' | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| short_description: Building an Object Depth Comparison Pipeline on Hugging Face | |
| # Object Depth Comparison Pipeline | |
| End-to-end pipeline that detects and segments objects in an image, | |
| estimates per-pixel depth, then reports the average depth of each object | |
| and the difference between them. | |
| Pipeline: | |
| 1. SAM3 — promptable concept segmentation (text prompt → boxes + masks per class, in one step) | |
| 2. Depth Anything V2 Large — monocular depth estimation | |
| 3. Average depth per mask | |
| 4. JSON comparison (depth per object + pairwise difference) | |
| > **Note:** `facebook/sam3` is a gated model on the Hugging Face Hub. The | |
| > environment running this app needs an `HF_TOKEN` (or a prior | |
| > `huggingface-cli login`) for an account that has accepted the SAM3 license, | |
| > otherwise model download will fail. | |