PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks. Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images... (read more)

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Object Reconstruction From A Single Image BUFF ML-PIFu (alternate) Point-to-surface distance (cm) 1.63 # 1
Chamfer (cm) 1.73 # 1
Surface normal consistency 0.133 # 1
3D Object Reconstruction From A Single Image BUFF ML-PIFu (end-to-end) Point-to-surface distance (cm) 1.88 # 2
Chamfer (cm) 1.81 # 2
Surface normal consistency 0.147 # 2
3D Object Reconstruction From A Single Image RenderPeople ML-PIFu (alternate) Point-to-surface distance (cm) 1.44 # 1
Chamfer (cm) 1.41 # 1
Surface normal consistency 0.111 # 1
3D Object Reconstruction From A Single Image RenderPeople ML-PIFu (end-to-end) Point-to-surface distance (cm) 1.66 # 2
Chamfer (cm) 1.55 # 2
Surface normal consistency 0.117 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet