[{"data":1,"prerenderedAt":224},["ShallowReactive",2],{"run:lego-brushcompat-opacdecay-30k":3,"run-findings:lego-brushcompat-opacdecay-30k":145},{"run":4,"config":20,"metrics":54,"curve":60,"assets":144},{"id":5,"title":5,"subtitle":6,"eyebrow":7,"date":8,"workspace":9,"commit":10,"tags":11,"verdict":19},"lego-brushcompat-opacdecay-30k","P1.D Stage 2 brush 互換 + opacity decay 30k full bench","Run summary · P1.D Stage 2 (splats 抑制 + Metal axis 1 効率化基盤)","2026-05-24","splat","031887c",[12,13,14,15,16,17,18],"p1-d","opacity-decay","lego-30k","brush-compat","premultiplied","stage-2","splat-efficient","partial",[21,24,27,30,33,36,39,42,45,48,51],{"key":22,"value":23},"dataset","\u002FUsers\u002Fotkrickey\u002Fdev\u002F3dgs-workspace\u002Fdatasets\u002Fnerf_synthetic\u002Flego",{"key":25,"value":26},"gt_convention","Premultiplied",{"key":28,"value":29},"iterations","30,000",{"key":31,"value":32},"seed","42",{"key":34,"value":35},"capacity","1,000,000 splats",{"key":37,"value":38},"sh_degree","3",{"key":40,"value":41},"loss","L1Ssim",{"key":43,"value":44},"lambda","0.200",{"key":46,"value":47},"ssim","window=7 sigma=1",{"key":49,"value":50},"backend.backward","Simd",{"key":52,"value":53},"backend.loss_path","Gpu",{"psnr":55,"wallclock":56,"wallclock_regress":57,"splats":58,"final_loss":59},36.10615158081055,"41m 54s",false,375146,"5.165299e-3",{"loss":61,"splats":126},{"iters":62,"values":94},[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],1,1000,2000,3000,4000,5000,6000,7000,8000,9000,10000,11000,12000,13000,14000,15000,16000,17000,18000,19000,20000,21000,22000,23000,24000,25000,26000,27000,28000,29000,30000,[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125],0.5938446521759033,0.051726363599300385,0.014371268451213837,0.00876694917678833,0.007387179881334305,0.006793309934437275,0.00635183323174715,0.006166964769363403,0.006000307854264975,0.005879946518689394,0.005871140398085117,0.005674093961715698,0.005623313598334789,0.0055536795407533646,0.0054626064375042915,0.005429072771221399,0.005354376509785652,0.005369709804654121,0.005370347760617733,0.0053934697061777115,0.005320888012647629,0.005347100552171469,0.005178855732083321,0.005251599475741386,0.005148155149072409,0.005170601420104504,0.0051399050280451775,0.005114785395562649,0.005053063854575157,0.00519897835329175,0.005165299400687218,{"iters":127,"values":128},[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],[129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,58,58,58,58,58,58,58,58,58,58,58,58,58,58,58,58],5207,11847,197353,292171,337590,362421,376853,384906,388892,390020,389552,387402,384530,381547,378271,{"has_renders":57,"has_splat":57},[146,178,208],{"id":147,"title":148,"date":149,"status":150,"polarity":151,"category":152,"axes":153,"tags":154,"task_code":166,"related_runs":167,"delta_psnr":172,"delta_wallclock":173,"rank":174,"verdict":175,"impact_summary":176,"detail_path":177},"p1-axis1-phase-g3-sh-progressive","Phase G.3 SH-progressive — 5k smoke -14% は artifact、30k full は **quality improvement + 0.28 dB** に reframe、stacked + G.1 で **Pareto sweet spot** (Lego -61% wallclock + 0.15 dB)","2026-05-25","stable","positive","design",[63],[155,156,157,158,159,160,14,161,162,163,164,165],"p1-axis1","phase-g","sh-progressive","compute-reduction","pareto-front","lego-5k","stacked-config","implementation","unit-tests","bit-exact","smoke-artifact","P1 Phase G.3",[168,169,170,171,5],"lego-phase-g3-sh-progressive-5k","lego-phase-g3-sh-progressive-30k","lego-phase-g1g3-stacked-15k","lego-phase-f1-baseline-5k","+0.15 dB stacked (vs Phase D)、+0.28 dB 30k single (vs Phase D)、-0.12 dB 5k smoke (許容)","**-61% stacked** (vs Phase D)、-1.9% 30k single、-13.9% 5k smoke (artifact)","high","pareto-sweet-spot-confirmed-chain-pending","Phase G compute reduction family の G.3 (SH-progressive growth) を実装 + bit-exact unit tests (11 件、cargo test 43 件 全 pass) + **3 layer の Lego 結果検証**。\u003Cstrong>(1) 5k smoke\u003C\u002Fstrong>: wallclock -13.9% \u002F splats -22% \u002F PSNR -0.12 dB、cascading splat reduction を観測。\u003Cstrong>(2) 30k full validation\u003C\u002Fstrong>: wallclock **-1.9%** (5k から大幅縮小)、splats **+30%** (5k から逆転)、PSNR **+0.28 dB** (quality improvement!)。5k smoke の cascading 効果は refine.stop_iter=1500 による artifact、30k では sh unlock 完了 (iter 3000) 後に refine が iter 15000 まで full SH で継続 → splats baseline より grow。\u003Cstrong>(3) G.1+G.3 stacked (max_steps=15000 + sh_progressive)\u003C\u002Fstrong>: Lego **16m13s \u002F 36.254 dB \u002F 428k splats** = Phase D 比 **-61% wallclock + 0.15 dB PSNR** で \u003Cstrong>Pareto sweet spot\u003C\u002Fstrong> 確定。\u003Cstrong>Key reframe\u003C\u002Fstrong>: G.3 は「speed win」ではなく「**quality improvement at no speed cost**」、stacked variant で G.1 speed と SH warmup quality gain を統合。\u003Cstrong>Implementation\u003C\u002Fstrong>: \u003Ccode>[trainer.sh_progressive]\u003C\u002Fcode> section (default disabled、全 backward compat)、\u003Ccode>CameraGpu\u003C\u002Fcode> struct を \u003Ccode>sh_degree\u003C\u002Fcode> (buffer layout) と \u003Ccode>active_sh_degree\u003C\u002Fcode> (per-iter eval) に分離。\u003Cstrong>Calibration data point\u003C\u002Fstrong>: Phase F 5 連続 falsification + G.3 5k smoke artifact = audit \u002F smoke overestimate 6 例目、「smoke は production scale を representative しない」が新教訓。8 scene chain validation pending。\u003Cstrong>卒論 narrative\u003C\u002Fstrong>: Phase F (kernel-level fail) → G.2 (architectural insight) → G.3 (algorithmic reframe: speed → quality + stacked Pareto) の 3 family 比較で「Apple Silicon native 最適化は \u003Cstrong>algorithmic compute reduction + early stop の組み合わせが Pareto-optimal\u003C\u002Fstrong>」という構造的 calibration。","\u002Ffindings\u002Fp1-axis1-phase-g3-sh-progressive\u002F",{"id":179,"title":180,"date":149,"status":150,"polarity":151,"category":181,"axes":182,"tags":185,"task_code":194,"related_runs":195,"delta_psnr":203,"delta_wallclock":204,"rank":174,"verdict":205,"impact_summary":206,"detail_path":207},"p1-d-multi-scene-rechain","P1.D multi-scene Phase D re-chain final — 8 scene mean 33.49 dB、brush mean 32.86 を +0.63 dB 上回り、universal win-win-win 実証","experiment",[63,183,184],2,3,[186,187,188,189,190,191,16,13,192,193],"p1","phase-d","milestone-m5","multi-scene","brush-parity","brush-超え","universal-win-win-win","rechain-final","P1.D multi-scene re-chain (M5 final)",[5,196,197,198,199,200,201,202],"chair-brushcompat-opacdecay-30k","ficus-brushcompat-opacdecay-30k","drums-brushcompat-opacdecay-30k","hotdog-brushcompat-opacdecay-30k","mic-brushcompat-opacdecay-30k","materials-brushcompat-opacdecay-30k","ship-brushcompat-opacdecay-30k","8 scene mean +0.63 dB vs brush paper (33.49 vs 32.86)","-61% total chain (13h+ → 5h 5m)","accepted-m5-complete","Phase D opacity_decay (rate=0.004 brush default) を 7 scene × 30k full chain bench、Lego val Phase D 30k と合わせて 8 scene 集計。**全 scene で baseline brushcompat 30k 比 PSNR + splats + wallclock すべて改善 (universal win-win-win)**: PSNR +0.18〜+1.42 dB \u002F splats -57〜-78% \u002F wallclock -39〜-69%。8 scene mean 33.49 dB vs brush paper 8 scene mean 32.86 dB = **+0.63 dB 上回り**、本実装が brush の multi-scene mean を decisive に超えた。brush 超え 3 scene (Lego val +4.07 \u002F drums +1.05 \u002F mic +1.02)、4 scene が brush 比 ±0.7 dB 圏内 (chair -0.02 \u002F hotdog -0.39 \u002F ship -0.01 \u002F materials -0.10)、最遠 scene でも ficus -0.65 で接近。全体 wallclock baseline chain (13h+) → Phase D re-chain 5h 5m (-61%)、mean splats 1.4M → 428k (-69%) で brush 282k に肉薄。P1.M5 完全達成 (Lego val > 36 dB ✅ + multi-scene mean > 32 dB ✅)、卒論 central evaluation table の final 数字確定、universal claim 完全実証。","\u002Ffindings\u002Fp1-d-multi-scene-rechain\u002F",{"id":209,"title":210,"date":149,"status":150,"polarity":151,"category":181,"axes":211,"tags":212,"task_code":215,"related_runs":216,"delta_psnr":219,"delta_wallclock":220,"rank":174,"verdict":221,"impact_summary":222,"detail_path":223},"p1-d-stage2-30k-results","P1.D Stage 2 — Lego brushcompat + opacity decay 30k = 36.106 dB、splats -56% \u002F wallclock -32%",[63,183,184],[186,187,188,13,190,213,16,14,17,18,214],"win-win-win","axis-1-prep","P1.D Stage 2 (M5 Lego val pass)",[5,217,218],"lego-brushcompat-base-30k","lego-brushcompat-opacdecay-5k","+0.92 dB vs baseline 30k (35.184 → 36.106)","-32% vs baseline 30k (1h 02m 18s → 41m 54s)","accepted-decisive-win","Lego brushcompat + opacity decay 30k で training-time eval 36.106 dB (val 100 view, brush convention, raw)、independent eval 36.163 dB (brush q8)。baseline 30k (35.184 dB) を **+0.92 dB 上回り**、splats を 846,689 → 375,146 に **-55.6% 削減**、wallclock を 1h 02m → 41m 54s に **-32% 短縮**。これは trade-off と想定していた PSNR\u002Fsplats\u002Fwallclock が **完全 win-win-win** に。M5 個別 scene gate (Lego brush conv > 36 dB) を val で達成、brush 自身 val 32.038 dB を +4.07 dB 上回り、本実装が brush を decisive に超えた。test subset (n=36) も +0.75 dB 改善 (33.315 → 34.065)、brush paper test 37.40 との gap を -3.34 dB まで縮小。Stage 1 smoke 推定 (splats -11.6%) を 30k で -56% に拡大、opacity decay の効果は iter 累積で増大することを実証。次 step は multi-scene Phase D 7 scene re-chain (chain 完了後 schedule)、低 wallclock + 低 splats での M5 multi-scene parity 完遂を狙う。","\u002Ffindings\u002Fp1-d-stage2-30k-results\u002F",1782449787767]