landmark-fit-repair

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Landmark Fit Repair

地标拟合修复

Bbox and IoU are too coarse for final mascot/logo matching. This skill turns named feature drift into recipe edits.

边界框（bbox）和交并比（IoU）对于吉祥物/标志的最终匹配来说精度太低。本技能将命名特征的偏差转化为配方编辑操作。

Landmark classes

地标类别

```
structural_tip
```
: outer part tips and extrema;
```
shell_corner
```
: face/shell/rim corners;
```
feature
```
: eyes, smile, brows, decals;
```
ring
```
: aura center/radius/dots;
```
depth_marker
```
: side/back/top thickness markers.

```
structural_tip
```
：外部部件的尖端和极值点；
```
shell_corner
```
：面部/外壳/边缘的边角；
```
feature
```
：眼睛、微笑、眉毛、贴花；
```
ring
```
：光环中心/半径/圆点；
```
depth_marker
```
：侧面/背面/顶部的厚度标记。

Workflow

工作流程

Define a landmark JSON for the source reference.
Detect or render corresponding product landmarks.
Compare by name and view.
Convert deltas into repair actions: move boundary control point, scale one component, shift feature curve, tune depth, or adjust aura radius.
Rebuild from recipe; do not hand-edit final geometry without updating the recipe/manifest.

为源参考文件定义地标JSON。
检测或渲染对应产品的地标。
按名称和视角进行对比。
将偏差转化为修复操作：移动边界控制点、缩放单个组件、偏移特征曲线、调整深度或修改光环半径。
根据配方重建模型；在未更新配方/清单的情况下，不得手动编辑最终几何形状。

Hard gates

硬性限制

No final export when named structural landmarks exceed tolerance.
Face features must be validated separately from body silhouette.
Aura/context landmarks must not affect base GLB acceptance.

当命名结构地标超出公差范围时，禁止最终导出。
面部特征必须与身体轮廓分开验证。
光环/环境地标不得影响基础GLB文件的验收。

Script

脚本

```
scripts/landmark_fit_report.py
```
compares two named-landmark JSON files and emits repair deltas.

```
scripts/landmark_fit_report.py
```
用于对比两个命名地标JSON文件，并输出修复偏差值。

Landmark JSON schema

地标JSON schema

json

{
  "schema": "landmarks.v1",
  "image_size": [width, height],
  "landmarks": [
    {"view":"front", "name":"leaf_top_tip", "class":"structural_tip", "x":627, "y":130}
  ]
}

For part masks, generate initial landmarks from extrema: top/bottom/left/right, centroid, and contour inflection points. Then rename them to semantic names before repair.

json

{
  "schema": "landmarks.v1",
  "image_size": [width, height],
  "landmarks": [
    {"view":"front", "name":"leaf_top_tip", "class":"structural_tip", "x":627, "y":130}
  ]
}

对于部件蒙版，从极值点生成初始地标：顶部/底部/左侧/右侧、质心和轮廓拐点。然后在修复前将它们重命名为语义化名称。