Phase G.3 SH-progressive growth + early stop の組み合わせで Lego の (wallclock, PSNR) Pareto curve を 7 点 (5k/7.5k/10k/12.5k/15k stacked/17.5k/20k/25k/30k) で精密 map。**stop_iter=10000 は brush (9m08s / 32.04 dB) を完全 Pareto-dominate** (同 wallclock + 3.89 dB)、**stop_iter=12500 は Phase D 30k (41m54s / 36.106 dB) を Pareto-dominate** (-71% wallclock + 0.15 dB)。ただし scene-validation で **ficus @ stop_iter=12500 = 30.103 dB (Phase D 比 -4.12 dB の大幅 fail)** を観測、**Lego sweet spot は scene-dependent と確定**、universal config では G.3 alone 30k (Phase G omnibus) が依然 best。**Phase H の最終 framing**: Lego は dense texture-rich scene で fast converge、sparse scene (ficus/mic 等) は full SH from start (no sh_progressive) または full 30k iter のいずれかが必要。axis 1 future work: scene-adaptive iter budget (Lego/chair/materials @ 12500、ficus/drums/hotdog/mic/ship @ 30000) で 8 scene mean を維持しつつ total wallclock を -40% 削減可能と推定。
Phase G.3 で G.3 alone 30k = universal Pareto improvement を確定した後、Lego の Pareto curve を stop_iter × 6 点 で精密 map。stop_iter=10000 が brush を完全 dominate、12500 が Phase D 30k を dominate (-71% wallclock + 0.15 dB)。ただし ficus @ stop_iter=12500 = -4.12 dB の大幅 fail で、Lego sweet spot は scene-dependent と確定。universal config は Phase G.3 alone 30k のまま、Lego sweet spot は dense texture scene 固有の Pareto improvement。
Lego stop_iter=12500 + sh_progressive = 11m48s / 36.259 dB、Phase D 30k (41m54s / 36.106 dB) を -71% wallclock + 0.15 dB で Pareto-dominate。stop_iter=10000 = 8m42s / 35.931 dB で brush (9m08s / 32.04 dB) を完全 dominate (同時間 +3.89 dB)。しかし ficus @ stop_iter=12500 = 30.103 dB (Phase D 34.22 比 **-4.12 dB の fail**)、sh_progressive warmup が sparse scene の高周波 detail 学習を遅延 + early stop で recovery 不可能、**Lego sweet spot は scene-dependent**。universal best config は依然 Phase G.3 alone 30k (8 scene mean 33.592 dB)、Lego sweet spot は dense texture scene の単独 Pareto improvement。**axis 1 future work**: scene-adaptive iter budget (Lego/chair/materials @ 12500、ficus/drums/mic 等 @ 30000) で 8 scene mean 33.5+ 維持しつつ total wallclock を 5h36m → ~3h に -40-50% 削減可能と推定 (検証 pending)。
| stop_iter | wallclock | PSNR (val) | splats | vs Phase D 30k | vs brush | Pareto status |
|---|---|---|---|---|---|---|
| 5,000 (smoke) | 1m37s | 31.509 | 64,330 | -4.60 | -0.53 | smoke baseline |
| 7,500 | 6m20s | 35.513 | 347,489 | -0.59 | +3.47 ★ | fast quality |
| **10,000** | **8m42s** | **35.931** | 385,007 | -0.18 | **+3.89 ★** | **brush dominate** ✓ |
| **12,500** | **11m48s** | **36.259** | 407,053 | **+0.15 ★** | +4.22 ★ | **Phase D 30k dominate** ✓ |
| 15,000 (stacked) | 16m13s | 36.254 | 427,882 | +0.15 ★ | +4.21 ★ | G.1+G.3 stacked (cf.) |
| 17,500 | 18m56s | 36.349 | 438,238 | +0.24 ★ | +4.31 ★ | marginal +0.09 dB only |
| 20,000 | 22m40s | 36.359 | 448,401 | +0.25 ★ | +4.32 ★ | marginal +0.01 dB only |
| 25,000 | 30m20s | 36.092 | 464,235 | -0.01 | +4.05 ★ | **anomaly** (training instability or variance) |
| 30,000 (G.3) | 41m07s | 36.384 | 487,741 | +0.28 ★ | +4.34 ★ | G.3 alone reference (universal) |
| scene | Phase D 30k | G.3 30k | G.1 stop15k | G.1+G.3 stacked 15k | Phase H @ 12500 | 12500 vs Phase D |
|---|---|---|---|---|---|---|
| Lego | 36.106 | 36.384 | 35.690 | 36.254 | **36.259** | **+0.153 ✓** |
| ficus | 34.220 | 34.281 | 32.431 | 31.066 | **30.103** | **-4.117 ✗✗** |
| mic | 36.380 | 36.624 | 30.541 | 30.328 | **30.346** | **-6.034 ✗✗** |
p1-axis1-phase-g-pareto-landscapep1-axis1-phase-g3-sh-progressivep1-d-multi-scene-rechainm4-brush-bench