Reflect ML Dashboard
Live from 5 machines — reflect-ml-02
Mirror Metric v5Live
Live from 5 machines · Best: reflect-ml-02
68/100
Mouth
30/40
Identity
12/25
Perceptual
13/20
Face
14/15
Most Realistic Render
ml-01 — step 62,000
MM 79/100Train PSNR: 37.6 dBLPIPS: 0.202SSIM: 0.859200,000 Gaussians
exp 191 clean baseline
Realism PushMirror Metric 68/100
Looking like a real person
The avatar now preserves the patient's identity and produces convincing facial expressions. Mouth quality and perceptual realism are the current focus — the gap between "good" and "mirror-like" is where we're pushing hardest.
What's Working
- +Best face reconstruction: 38.5 dB — the avatar looks like the person
- +5 machines training simultaneously — testing multiple approaches in parallel
What's Next
- →Close the perceptual gap — making fine details indistinguishable from reality
- →Optimize for real-time rendering at 60fps on consumer hardware
- →Currently testing: cnn deform, clean baseline, expr opacity
Challenges We're Solving
- •We've run 231 experiments so far. Not all succeed, and that's by design — each one narrows down what works best
- •Real-time quality at 60fps requires balancing visual fidelity with rendering speed — we're solving both simultaneously
GPU Fleet — 5 Active
Live
| Machine | Experiment | Step | Train PSNR / LPIPS | MM |
|---|---|---|---|---|
| reflect-ml-02 | exp 192 cnn deform 32% complete | 63,150 | 32.9 dB Train 0.2028 LPIPS | 68 |
| reflect-ml-01 | exp 191 clean baseline 33% complete | 65,600 | 32.2 dB Train 0.2200 LPIPS | 65 |
| reflect-cart-02 | exp 194 expr opacity 7% complete | 13,750 | 31.1 dB Train 0.2531 LPIPS | 59 |
| reflect-cart-01 | exp 193 mouth weight 21% complete | 41,200 | 28.8 dB Train 0.2552 LPIPS | 52 |
| reflect-gpu | exp 195 blendshapes 12% complete | 23,450 | 17.5 dB Train 0.4941 LPIPS | 5 |
Top Experiments
All runs →1exp 187 cnn relaxed early deformcart6730.4 dB Train2exp 165 phase2 multisessionml-016630.1 dB Train3exp 167 phase2 cart01 singlecart6629.2 dB Train4exp 166 phase2 densify200kml-026628.7 dB Train5exp 159 audit baselinecart6329.5 dB Train6exp 161 clean ml02ml-026229.3 dB Train7exp 184 cnn onlyml-026228.1 dB Train8exp 170 antiblur lossescart6128.9 dB Train
Best Run Per Machine
ml-01exp 165 phase2 multisession
66MM
30.1 dB Train200.0K GaussiansStep 182,40057 runs total
ml-02exp 166 phase2 densify200k
66MM
28.7 dB Train200.0K GaussiansStep 181,05050 runs total
cartexp 187 cnn relaxed early deform
67MM
30.4 dB Train200.0K GaussiansStep 30,85043 runs total
cart-02exp 161 clean cart02
61MM
28.4 dB Train200.0K GaussiansStep 60,00041 runs total
raiderexp 161 clean raider
57MM
29.3 dB Train200.0K GaussiansStep 60,00045 runs total