DeformNet, Or A Tale of Broken Chairs

Some bonkers stuff conjured up in the process of doing research | October 18, 2017

I spent about half of his year so far devoted to my first major research project at Stanford - DeformNet. The gist of the project was to create 3D models of objects based on a single 2D image of the object, by deforming the 3D model of a similar object. It took months to get working properly, but all that work eventually led to a paper - “DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image” - with its very own Arxiv post and project page. But, it also led to much more. It led to horrific, bizzare, and delightful failures.

All research projects, and projects in general, face a sequence of failures before their eventual success (or demise). Unlike the eventual success, the failures are typically barely catalogued, and certainly not freely shared with the world. But not DeformNet! Due to its nature as computer vision research, and in particular research on deforming 3D models of objects, DeformNet generated uniquelly broken and surreal imagery in its many months of development. So much so, that I was inspired to capture and share said imagery with my Friends on facebook. And now, dear reader, I shall share it with you! Without further ado, or any further context or explanation, please enjoy: