Depth Estimation on Goliath Face 12 cameras, 16 frames, 4 subjects 47
0.021RMSETHFM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| THFMDecoder Training=false, 4 Dense Task=false, 2 Sparse Task=false, Token Mask=false2026.03 | 0.021 | 1.1 | |
| Sapiens-2BEvaluation Protocol=Our Eval2026.03 | 0.022 | 1.1 | |
| DAVID-BaseEvaluation Protocol=Our Eval2026.03 | 0.022 | 1.2 | |
| DAVID-LargeEvaluation Protocol=Our Eval2026.03 | 0.022 | 1.2 | |
| Sapiens-0.3BEvaluation Protocol=Our Eval2026.03 | 0.023 | 1.3 | |
| THFMDecoder Training=true, 4 Dense Task=true, 2 Sparse Task=false, Token Mask=false2026.03 | 0.026 | 1.6 | |
| THFMDecoder Training=true, 4 Dense Task=true, 2 Sparse Task=true, Token Mask=true2026.03 | 0.033 | 2.3 | |
| Depth-ProEvaluation Protocol=Our Eval2026.03 | 0.034 | 2.3 | |
| DAVID-LargeEvaluation Protocol=Results from DAVID2026.03 | 0.14 | 0.9 | |
| DAVID-BaseEvaluation Protocol=Results from DAVID2026.03 | 0.142 | 0.9 | |
| Sapiens-2BEvaluation Protocol=Results from DAVID2026.03 | 0.158 | 0.9 | |
| Sapiens-0.3BEvaluation Protocol=Results from DAVID2026.03 | 0.179 | 1.2 | |
| MiDaS-DPT_LEvaluation Protocol=Results from DAVID2026.03 | 0.224 | 1.6 | |
| DepthAnythingV2-LEvaluation Protocol=Results from DAVID2026.03 | 0.229 | 1.7 | |
| Depth-ProEvaluation Protocol=Results from DAVID2026.03 | 0.295 | 2 |