You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit e2d7974
Browse filesBrowse the repository at this point in the historyBrowse files
docs(showcase): regenerate the hay-bale gallery page
The page embeds the piece README, whose texel figure was corrected after
the last build.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Signed-off-by: TMHSDigital <154358121+TMHSDigital@users.noreply.github.com>
Copy file name to clipboardExpand all lines: docs/gallery/hay-bale/index.html
+2-2Lines changed: 2 additions & 2 deletions
Original file line number
Diff line number
Diff line change
@@ -289,7 +289,7 @@ <h2>How the belts are built</h2>
289
289
<h2>Budgets</h2>
290
290
<p>Declared as named constants; every gate <strong>recomputes</strong> from the mesh, materials, UVs, evaluated LOD, collider, or export file. Measurements below are identical on 4.5.11, 5.1.2 and 5.2.1 — construction uses no RNG and no version-dependent operator.</p>
291
291
<divclass="table-wrap"><table><thead><tr><thscope="col">Axis</th><thscope="col">Declared</th><thscope="col">Measured (4.5.11 / 5.1.2 / 5.2.1)</th></tr></thead><tbody><tr><td>Base triangles</td><td>1700–2400</td><td>2044 on all three</td></tr><tr><td>LOD1 ratio</td><td>0.32–0.62 of base</td><td>0.5000</td></tr><tr><td>LOD2 ratio</td><td>0.10–0.35 of base</td><td>0.2192</td></tr><tr><td>Materials</td><td>exactly 2 distinct, ≥24 hay, ≥24 twine</td><td>2 slots, 1436 hay, 304 twine</td></tr><tr><td>UVs</td><td>in <code>0..1</code>, AABB overlap ≤ 1e-5</td><td>in range, overlap 0</td></tr><tr><td>Outer AABB</td><td>(0.921, 0.508, 0.417) m ± 0.01</td><td>(0.9208, 0.5075, 0.4165)</td></tr><tr><td>Grounded zmin</td><td>within 1e-4 of 0</td><td>0.000000</td></tr><tr><td>Hygiene</td><td>loose/nonman/zero-area/doubles/n-gons/<strong>z-fight</strong> = 0</td><td>all 0</td></tr><tr><td>Shell count</td><td>exactly 5 (loaf, 2 belts, 2 loops)</td><td>5</td></tr><tr><td><strong>Belt wrap zmin</strong></td><td>each belt shell ≤ 0.006 m</td><td>0.001460 both</td></tr><tr><td><strong>Belt seat depth</strong></td><td>every station in [0.002, 0.020] m</td><td>0.00400..0.01114 over 20/20 stations, both belts</td></tr><tr><td><strong>Mirror symmetry</strong></td><td>belts and loops matched within 5e-4 m</td><td>0.000000</td></tr><tr><td><strong>Loaf mirror</strong></td><td>every loaf vertex has an X-mirror partner within 2e-4 m</td><td>0.000093</td></tr><tr><td><strong>Cinch depth</strong></td><td>mid-span minus waist in [0.006, 0.020] m</td><td>0.01053</td></tr><tr><td>Loaf X × Z</td><td>(0.921, 0.393) m ± 0.02</td><td>(0.9208, 0.3931)</td></tr><tr><td>Hay–twine gap</td><td>BVH surface < 0.008 m</td><td>0.00009</td></tr><tr><td>Collider tris</td><td>≤ 400</td><td>140</td></tr><tr><td>Bake texels</td><td>smallest UV cell ≥ 12 px at the baked resolution</td><td>22.43 px at 1024 px</td></tr><tr><td>Export</td><td>written, size > 0</td><td>203508 / 203508 / 203496 bytes</td></tr></tbody></table></div>
292
-
<p>DECIMATE COLLAPSE triangle counts are <strong>not</strong> guaranteed identical across series — the gate is a ratio band, not an exact count. Bake pixels are stochastic; the gate is <code>has_data</code> plus operator <code>FINISHED</code>, not byte-identity, plus the texel floor. The bake was 256 px, which left about 8 texels per UV cell and smeared neighbouring cells' normals into streaks across the straw; at 1024 px with a 0.02 m cage (was 0.04, which reached the twine standing proud of the loaf) every cell gets 22. Export byte counts differ by 12 B on 5.2.1 (glTF serializer), which is not a gated axis; every geometric figure above is identical on all three binaries.</p>
292
+
<p>DECIMATE COLLAPSE triangle counts are <strong>not</strong> guaranteed identical across series — the gate is a ratio band, not an exact count. Bake pixels are stochastic; the gate is <code>has_data</code> plus operator <code>FINISHED</code>, not byte-identity, plus the texel floor. The bake was 256 px, which left 5.6 texels per UV cell and smeared neighbouring cells' normals into streaks across the straw; at 1024 px with a 0.02 m cage (was 0.04, which reached the twine standing proud of the loaf) every cell gets 22. Export byte counts differ by 12 B on 5.2.1 (glTF serializer), which is not a gated axis; every geometric figure above is identical on all three binaries.</p>
293
293
<p>The export is deleted once its size is measured. Blender sets <code>TMPDIR</code> from its own preference, which resolves to the working directory on a stock portable build, so <code>tempfile.gettempdir()</code> is the repo root under CI and every run used to leave a <code>.glb</code> behind.</p>
294
294
<h3>Why these budgets and not an AABB</h3>
295
295
<p><code>zmin</code> alone cannot see a belt that stops at the bottom edge: the loaf still grounds the box. A single global hay-twine gap cannot see a wrap that hugs one side and gaps the other. A bounding box cannot see two belts 5.4 mm out of step, or a flank with no waist in it. Each of the five budgets in bold above exists because a defect got past everything else and had to be found by looking at a render.</p>
@@ -431,7 +431,7 @@ <h2>Source</h2>
431
431
UV_EPS = <spanclass="n">1e-4</span>
432
432
UV_OVERLAP_MAX = <spanclass="n">1e-5</span>
433
433
COLLIDER_TRIS_MAX = <spanclass="n">400</span>
434
-
<spanclass="c"># One UV cell per face: at 256 px each cell got about 8 texels, and the</span>
434
+
<spanclass="c"># One UV cell per face: at 256 px each cell got 5.6 texels, and the</span>
435
435
<spanclass="c"># bilinear lookup smeared neighbouring cells' normals into streaks across</span>
436
436
<spanclass="c"># the straw (tavern-stool's defect). 1024 px, with a floor asserted.</span>
0 commit comments