what are the baselines?

How to create the 3D mesh?

Deform from sphere or ellipsoid mesh

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer

Learning Category-Specific Mesh Reconstruction from Image Collections

Pixel2mesh

pixel2mesh++

Create Point Cloud

Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction

Deep + structure from motion

DeepSFM: Structure From Motion Via Deep Bundle Adjustment

Deep Non-Rigid Structure from Motion

Deep nrsfm++: Towards 3d reconstruction in the wild

relevant medium post

Unsupervised Deep Persistent Monocular Visual Odometry and Depth Estimation in Extreme Environments

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

What happens when we implement the techniques on the Liberty statue? (direct transfer)