Mesh R-CNN

ICCV 2019 Georgia GkioxariJitendra MalikJustin Johnson

Rapid advances in 2D perception have led to systems that accurately detect objects in real-world images. However, these systems make predictions in 2D, ignoring the 3D structure of the world... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
3D Shape Modeling Pix3D S1 Mesh R-CNN box AP 94.0 # 1
3D Shape Modeling Pix3D S1 Mesh R-CNN mask AP 88.4 # 1
3D Shape Modeling Pix3D S1 Mesh R-CNN mesh AP 51.1 # 1
3D Shape Modeling Pix3D S2 Mesh R-CNN box AP 72.2 # 1
3D Shape Modeling Pix3D S2 Mesh R-CNN mask AP 63.9 # 1
3D Shape Modeling Pix3D S2 Mesh R-CNN mesh AP 28.8 # 1