3D Face Reconstruction On Now Benchmark 1

评估指标

Mean Reconstruction Error (mm)
Median Reconstruction Error
Stdev Reconstruction Error (mm)

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
3DMM-CNN2.331.842.05Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
PRNet1.981.501.88Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
UMDFA1.891.521.57“Look Ma, no landmarks!” – Unsupervised, Model-based Dense Face Alignment-
MGCNet1.871.312.63Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency
SynergyNet1.591.271.31Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
Dib et al. 20211.571.261.31Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing-
3DDFA_V21.571.231.39Towards Fast, Accurate and Stable 3D Dense Face Alignment
Deng et al. 20191.541.231.29Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
RingNet1.531.211.31Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
FLAME template1.531.211.31Learning a model of facial shape and expression from 4D scans-
PIXIE1.491.181.25Collaborative Regression of Expressive Bodies using Moderation
Deep3DFaceRecon PyTorch1.411.111.21Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
DECA1.381.091.18Learning an Animatable Detailed 3D Face Model from In-The-Wild Images
FOCUS1.301.041.10Robust Model-based Face Reconstruction through Weakly-Supervised Outlier Segmentation
DenseLandmarks (Single-view)1.281.021.083D face reconstruction with dense landmarks-
MICA1.110.900.92Towards Metrical Reconstruction of Human Faces
DenseLandmarks (Multi-view)1.010.810.843D face reconstruction with dense landmarks-
0 of 17 row(s) selected.
3D Face Reconstruction On Now Benchmark 1 | SOTA | HyperAI超神经