docs: add Training data & PII section (submission-guideline compliance)

README.md

@@ -71,6 +71,16 @@ The fp16 model compiles to **234 / 234 nodes on the LiteRT GPU delegate
 (best 1.1 ms). `RESIZE_BILINEAR align_corners=True` is GPU-supported as-is; no
 model change needed.
 
+## Training data & PII
+
+This is a weights-exact format conversion of Intel ISL's **MiDaS v2.1 small**; no new
+training was performed. MiDaS was trained for monocular depth on a **mix of ~10 public
+depth datasets** (e.g. ReDWeb, DIML, MegaDepth, WSVD, 3D Movies). These contain photos of
+real scenes that may incidentally include people and other PII; none was deliberately
+collected and this conversion adds none. The model outputs a relative-depth map only and
+performs no identification. Apply your own content/PII filtering before deployment. See the
+original [MiDaS](https://github.com/isl-org/MiDaS) repo for dataset details.
+
 ## License & attribution
 
 - **MiDaS** weights: MIT (Intel ISL).