Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Pix3D

3DImagesCC BY 4.0Introduced 2018-01-01

The Pix3D dataset is a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related tasks including reconstruction, retrieval, viewpoint estimation, etc.

Source: http://pix3d.csail.mit.edu/ Image Source: http://pix3d.csail.mit.edu/

Benchmarks

1 Image, 2*2 Stitchi/Percentage correct 3D/Percentage correct 3D/CD 3D/EMD 3D/IoU 3D/R@1 3D/R@16 3D/R@2 3D/R@32 3D/R@4 3D/R@8 3D Shape Reconstruction/CD 3D Shape Reconstruction/EMD 3D Shape Reconstruction/IoU Pose Estimation/Percentage correct

Related Benchmarks

Pix3D S1/3D Shape Modeling/box AP Pix3D S1/3D Shape Modeling/mask AP Pix3D S1/3D Shape Modeling/mesh AP Pix3D S2/3D Shape Modeling/box AP Pix3D S2/3D Shape Modeling/mask AP Pix3D S2/3D Shape Modeling/mesh AP

Statistics

Papers: 142
Benchmarks: 15

Links

Tasks

1 Image, 2*2 Stitchi 3D 3D Shape Classification 3D Shape Modeling 3D Shape Reconstruction Pose Estimation