SIFU

Reported on 4 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Lifelike 3D Human GenerationonTHuman2.0 Dataset
CLIP Similarity· 2023-12-10
0.8663
best: 0.9235 (Human-VDM)
SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction arXiv:2312.06704
Lifelike 3D Human GenerationonTHuman2.0 Dataset
LPIPS· 2023-12-10
0.15
best: 0.0957 (Human-VDM)
SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction arXiv:2312.06704
Lifelike 3D Human GenerationonTHuman2.0 Dataset
PSNR· 2023-12-10
16.46
best: 20.068 (Human-VDM)
SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction arXiv:2312.06704
Lifelike 3D Human GenerationonTHuman2.0 Dataset
SSIM· 2023-12-10
0.7931
best: 0.9228 (Human-VDM)
SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction arXiv:2312.06704