Differentiable Volumetric Rendering

Paper | Supplementary | Spotlight Video | Blog Entry | Presentation | Interactive Slides | Project Page

I have made some changes in the original code to and have only tested the pre-trained models provided by the original github repository.

This repository has basically trained a model on ShapeNet dataset and thus, we can create 3d models of objects in the ShapeNet dataset using single 2D images of that object.

This repository contains the code for the paper Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision.

You can find detailed usage instructions for training your own models and using pre-trained models in the docx file