4D Generation on Consistent4D
0.0823LPIPSSpatio-Temporal Attention Chain + CPE
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Spatio-Temporal Attention Chain + CPEAligned=true2026.05 | 0.0823 | 0.9468 | — | — | — | — | — | 0.0319 | |
| Ours + CPEAligned=true2026.05 | 0.0823 | 0.9468 | — | — | — | — | — | 0.0319 | |
| L4GMAligned=true2026.05 | 0.0988 | 0.9397 | — | — | — | — | — | 0.0487 | |
| L4GMAligned=true2026.05 | 0.0988 | 0.9397 | — | — | — | — | — | 0.0487 | |
| SkeletonGaussian2026.02 | 0.125 | 0.923 | 847.8 | — | — | — | — | — | |
| STAG4D2026.02 | 0.126 | 0.909 | 992.2 | — | — | — | — | — | |
| SG4DAligned=false2026.05 | 0.1359 | 0.9009 | — | — | — | — | — | 0.0966 | |
| SG4DAligned=false2026.05 | 0.1359 | 0.9009 | — | — | — | — | — | 0.0966 | |
| 4DGenframes=162026.02 | 0.137 | 0.909 | 913.1 | — | — | — | — | — | |
| Spatio-Temporal Attention ChainAligned=false2026.05 | 0.1423 | 0.9112 | — | — | — | — | — | 0.0823 | |
| OursAligned=false2026.05 | 0.1423 | 0.9112 | — | — | — | — | — | 0.0823 | |
| DreamGaussian4D2026.02 | 0.143 | 0.913 | 994.11 | — | — | — | — | — | |
| ActionMeshAligned=false2026.05 | 0.1458 | 0.9012 | — | — | — | — | — | 0.0939 | |
| ActionMeshAligned=false2026.05 | 0.1458 | 0.9012 | — | — | — | — | — | 0.0939 | |
| GVFD2026.06 | 0.1487 | 0.8142 | 821.75 | — | — | — | — | 0.1706 | |
| SS4D2025.12 | 0.149 | 0.947 | 455 | 18.9 | 0.843 | — | — | — | |
| Step1X-3DAligned=false2026.05 | 0.1524 | 0.904 | — | — | — | — | — | 0.1106 | |
| Step1X-3DAligned=false2026.05 | 0.1524 | 0.904 | — | — | — | — | — | 0.1106 | |
| MORPHOS2026.06 | 0.1531 | 0.8571 | 1,013.11 | — | — | — | — | 0.1849 | |
| STD-4D DiffusionInput Modality=3D2026.03 | 0.16 | — | 465.3 | 17.6 | 0.85 | 0.95 | 0.84 | — | |
| Consistent4D2026.02 | 0.161 | 0.877 | 1,518.5 | — | — | — | — | — | |
| L4GM2026.06 | 0.1633 | 0.8374 | 825.64 | — | — | — | — | 0.2063 | |
| GVFDAligned=false2026.05 | 0.1691 | 0.8601 | — | — | — | — | — | 0.1467 | |
| GVFDAligned=false2026.05 | 0.1691 | 0.8601 | — | — | — | — | — | 0.1467 | |
| STD-4D DiffusionInput Modality=Image2026.03 | 0.17 | — | 477.7 | 17.3 | 0.84 | 0.93 | 0.82 | — | |
| Mesh4D2026.06 | 0.1769 | 0.7968 | 1,189.67 | — | — | — | — | 0.2507 | |
| Diffusion4DInput Modality=3D2026.03 | 0.18 | — | 482.4 | 17.2 | 0.83 | 0.91 | 0.81 | — | |
| STD-4D DiffusionInput Modality=Text2026.03 | 0.19 | — | 523.4 | 16.8 | — | 0.85 | 0.72 | — | |
| Diffusion4DInput Modality=Image2026.03 | 0.19 | — | 490.2 | 16.8 | 0.82 | 0.9 | 0.8 | — | |
| Diffusion4DInput Modality=Text2026.03 | 0.2 | — | 684 | 15.3 | — | 0.82 | 0.69 | — | |
| STAG4D2025.12 | 0.204 | 0.89 | 740 | 16.89 | 0.821 | — | — | — | |
| Motion3242026.06 | 0.2044 | 0.8285 | 936.68 | — | — | — | — | 0.2013 | |
| Animate124Input Modality=Text2026.03 | 0.21 | — | 720.5 | 15 | — | 0.75 | 0.58 | — | |
| DG4D2025.12 | 0.215 | 0.896 | 641 | 15.47 | 0.785 | — | — | — | |
| L4GM2025.12 | 0.219 | 0.908 | 596 | 15.69 | 0.803 | — | — | — | |
| Consistent4D2025.12 | 0.228 | 0.886 | 674 | 13.66 | 0.768 | — | — | — | |
| 4DFYInput Modality=Text2026.03 | 0.23 | — | 1,042.3 | 14.2 | — | 0.78 | 0.61 | — | |
| TRELLIS2026.06 | 0.2479 | 0.8044 | 1,488.32 | — | — | — | — | 0.2962 | |
| STAG4DInput Modality=Image2026.03 | 0.27 | — | 675.4 | 15.2 | 0.76 | 0.86 | 0.72 | — | |
| 4DGenInput Modality=Image2026.03 | 0.31 | — | 736.6 | 14.4 | 0.69 | 0.84 | 0.71 | — |