Human-Object Interaction Generation on OMOMO (test)
0FIDGround Truth
Evaluation Results
| Method | Links | ||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Ground Truthbatch size=2562026.03 | 0 | 0.318 | 0.56 | 0.731 | 1.499 | 7.4 | — | — | 0.012 | — | 0.067 | 0.262 | 100 | 100 | 100 | — | — | — | — | — | — | — | — | — | — | — | |
| Real Motion2026.04 | 0 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0 | 0 | 26 | 73 | 66 | 1.29 | 0 | 0 | 0 | 0 | — | |
| Real motion2025.03 | 0.001 | 0.247 | 0.398 | 0.504 | 1.05 | 1.356 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ChainHOIPost-processing (AIC)=true2025.03 | 0.098 | 0.266 | 0.434 | 0.549 | 1.023 | 1.348 | 0.12 | 0.021 | 0.09 | 0.136 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LIGHTbatch size=256, guidance=true2026.03 | 0.099 | 0.302 | 0.538 | 0.707 | 1.657 | 7.443 | — | — | 0.013 | — | 0.1 | 0.194 | 94 | 85.1 | 88.1 | — | — | — | — | — | — | — | — | — | — | — | |
| ChainHOI2025.03 | 0.112 | 0.264 | 0.431 | 0.545 | 1.023 | 1.35 | 0.263 | 0.019 | 0.089 | 0.283 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CHOISbatch size=2562026.03 | 0.132 | 0.291 | 0.515 | 0.676 | 1.746 | 7.417 | — | — | 0.019 | — | 0.096 | 0.23 | 93.7 | 90 | 91 | — | — | — | — | — | — | — | — | — | — | — | |
| LIGHTbatch size=256, guidance=false2026.03 | 0.132 | 0.279 | 0.514 | 0.673 | 1.811 | 7.395 | — | — | 0.012 | — | 0.104 | 0.192 | 94 | 84.4 | 87.5 | — | — | — | — | — | — | — | — | — | — | — | |
| InterDiffbatch size=2562026.03 | 0.163 | 0.312 | 0.548 | 0.718 | 1.587 | 7.387 | — | — | 0.025 | — | 0.1 | 0.206 | 94 | 86.3 | 89 | — | — | — | — | — | — | — | — | — | — | — | |
| MDMFinetuning=true2025.03 | 0.164 | 0.123 | 0.208 | 0.278 | 1.228 | 1.333 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Text2HOIbatch size=2562026.03 | 0.168 | 0.286 | 0.513 | 0.655 | 1.832 | 7.359 | — | — | 0.02 | — | 0.127 | 0.163 | 91.9 | 75.7 | 80.7 | — | — | — | — | — | — | — | — | — | — | — | |
| MDMvariant=Star2025.03 | 0.169 | 0.12 | 0.208 | 0.281 | 1.191 | 1.319 | 0.56 | 0.022 | 0.134 | 0.686 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HOI-DiffPost-processing (AIC)=true2025.03 | 0.245 | 0.14 | 0.253 | 0.34 | 1.183 | 1.303 | 0.301 | 0.017 | 0.136 | 0.331 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CHOISvariant=Star2025.03 | 0.251 | 0.133 | 0.254 | 0.343 | 1.193 | 1.334 | 0.323 | 0.021 | 0.151 | 0.433 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| InerDiff2025.03 | 0.253 | 0.118 | 0.21 | 0.281 | 1.167 | 1.227 | 0.472 | 0.015 | 0.139 | 0.585 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PriorMDMvariant=Star2025.03 | 0.329 | 0.147 | 0.219 | 0.277 | 1.2 | 1.181 | 0.588 | 0.025 | 0.115 | 0.755 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HOI-Diff2025.03 | 0.48 | 0.114 | 0.198 | 0.268 | 1.221 | 1.124 | 0.678 | 0.022 | 0.151 | 0.433 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| InfBaGelSampling steps=162026.04 | 0.68 | — | — | — | — | — | — | — | — | — | — | — | 78 | 73 | 73 | 3.06 | 3.7 | 32 | 67 | 60 | 2.49 | 12.11 | 7.93 | 15.93 | 1.02 | 29.31 | |
| HOI-Diffbatch size=2562026.03 | 0.987 | 0.221 | 0.403 | 0.542 | 2.52 | 7.248 | — | — | 0.021 | — | 0.131 | 0.135 | 86.2 | 69.6 | 73.9 | — | — | — | — | — | — | — | — | — | — | — | |
| CHOIS2026.04 | 1.01 | — | — | — | — | — | — | — | — | — | — | — | 78 | 63 | 66 | 5.28 | 5.73 | 32 | 68 | 53 | 2.52 | 13.93 | 8.42 | 17.74 | 0.92 | 28.01 | |
| InfBaGelSampling steps=82026.04 | 1.78 | — | — | — | — | — | — | — | — | — | — | — | 78 | 68 | 70 | 2.99 | 3.89 | 34 | 67 | 56 | 2.61 | 11.97 | 8.47 | 15.59 | 1.02 | 60.94 | |
| LINGO2026.04 | 2.57 | — | — | — | — | — | — | — | — | — | — | — | 70 | 46 | 50 | 17.57 | 3.76 | 50 | 58 | 41 | 4.8 | 16.39 | 10.28 | 27.64 | 1.33 | 28.86 | |
| InfBaGelSampling steps=12026.04 | 3.41 | — | — | — | — | — | — | — | — | — | — | — | 79 | 64 | 66 | 2.93 | 4.19 | 36 | 63 | 52 | 2.83 | 11.92 | 8.88 | 15.4 | 1.02 | 1,566.71 | |
| ROG2026.04 | 5.46 | — | — | — | — | — | — | — | — | — | — | — | 80 | 68 | 70 | 26.68 | 19.43 | 49 | 53 | 54 | 5.86 | 13.37 | 21.28 | 31.89 | 1.14 | 9.07 |