3D Face Reconstruction On Realy
평가 지표
@cheek
@forehead
@mouth
@nose
all
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
모델 이름 | @cheek | @forehead | @mouth | @nose | all |
---|---|---|---|---|---|
self-supervised-monocular-3d-face | 1.665 (±0.644) | 2.248 (±0.508) | 1.409 (±0.418) | 1.827 (±0.383) | 1.787 |
3d-face-reconstruction-with-the-geometric | 1.110 (±0.328) | 1.809 (±0.394) | 1.237 (±0.375) | 1.584 (±0.308) | 1.435 |
accurate-3d-face-reconstruction-with-weakly | 1.528 (±0.501) | 2.015 (±0.449) | 1.368 (±0.439) | 1.719 (±0.354) | 1.657 |
towards-high-fidelity-nonlinear-3d-face | 1.918 (±0.801) | 4.582 (±1.488) | 2.375 (±0.599) | 2.936 (±0.810) | 2.953 |
expnet-landmark-free-deep-3d-facial | 1.717 (±0.590) | 3.084 (±1.005) | 1.912 (±0.450) | 2.509 (±0.486) | 2.306 |
towards-realistic-generative-3d-face-models | 1.141 (±0.303) | 2.102 (±0.512) | 2.087 (±0.839) | 1.656 (±0.374) | 1.746 |
joint-3d-face-reconstruction-and-dense | 1.863 (±0.698) | 2.429 (±0.588) | 1.838 (±0.637) | 1.923 (±0.518) | 2.013 |
a-perceptual-shape-loss-for-monocular-3d-face | 1.593 (±0.540) | 2.350 (±0.551) | 1.876 (±0.563) | 1.708 (±0.349) | 1.882 |
mosar-monocular-semi-supervised-model-for | 1.128 (±0.303) | 1.950 (±0.559) | 1.424 (±0.462) | 1.499 (±0.366) | 1.500 |
ffhq-uv-normalized-facial-uv-texture-dataset | 0.943 | 1.631 | 1.339 | 1.681 | 1.399 |
ganfit-generative-adversarial-network-fitting | 1.329 (±0.504) | 2.402 (±0.545) | 1.812 (±0.544) | 1.928 (±0.490) | 1.868 |
learning-an-animatable-detailed-3d-face-model | 1.443 (±0.498) | 2.457 (±0.559) | 2.802 (±0.868) | 2.138 (±0.461) | 2.210 |
a-hierarchical-representation-network-for | 1.072 (±0.333) | 1.995 (±0.476) | 1.357 (±0.523) | 1.722 (±0.330) | 1.537 |
synergy-between-3dmm-and-3d-landmarks-for | 1.647 (±0.622) | 2.679 (±0.741) | 1.731 (±0.502) | 2.026 (±0.532) | 2.021 |
emoca-emotion-driven-monocular-face-capture | 1.495 (±0.469) | 2.595 (±0.631) | 2.929 (±1.106) | 2.532 (±0.539) | 2.388 |
hiface-high-fidelity-3d-face-reconstruction | 1.291 (±0.362) | 1.324 (±0.334) | 1.450 (±0.413) | 1.036 (±0.280) | 1.275 |
towards-metrical-reconstruction-of-human | 1.099 (±0.324) | 2.374 (±0.683) | 3.478 (±1.204) | 1.585 (±0.325) | 2.134 |
learning-to-regress-3d-face-shape-and | 2.028 (±0.720) | 2.995 (±0.908) | 2.074 (±0.616) | 1.934 (±0.458) | 2.258 |
emoca-emotion-driven-monocular-face-capture | 1.438 (±0.501) | 2.426 (±0.641) | 2.679 (±1.112) | 1.868 (±0.387) | 2.103 |
learning-an-animatable-detailed-3d-face-model | 1.479 (±0.535) | 2.394 (±0.576) | 2.516 (±0.839) | 1.697 (±0.355) | 2.010 |
towards-fast-accurate-and-stable-3d-dense-1 | 1.757 (±0.642) | 2.447 (±0.647) | 1.597 (±0.478) | 1.903 (±0.517) | 1.926 |
sadrnet-self-aligned-dual-face-regression | 1.856 (±0.701) | 2.413 (±0.537) | 1.591 (±0.488) | 1.791 (±0.542) | 1.913 |
hiface-high-fidelity-3d-face-reconstruction | 1.342 (±0.384) | 1.331 (±0.347) | 1.461 (±0.430) | 1.054 (±0.317) | 1.297 |
self-supervised-3d-face-reconstruction-via-1 | 1.456 (±0.485) | 2.384 (±0.578) | 1.448 (±0.406) | 2.779 (±0.835) | 2.017 |