Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling

We study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Shape Classification Pix3D MarrNet extension (w/o Pose) R@1 0.53 # 1
R@16 0.85 # 1
R@2 0.62 # 1
R@32 0.90 # 1
R@4 0.71 # 1
R@8 0.78 # 1
3D Shape Reconstruction Pix3D MarrNet extension (w/ Pose) CD 0.119 # 2
EMD 0.118 # 2
TIoU 0.282 # 1

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