# Inverse Transport Networks

arXiv: https://arxiv.org/abs/1809.10820 · HTML: https://mlsanity.com/paper/1809.10820/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2018.

## Built on by (most cited first, 2 of 2)

- [Physics vs. Learned Priors: Rethinking Camera and Algorithm Design for Task-Specific Imaging](https://mlsanity.com/paper/2204.09871/) (2022)
- [Visual Tomography: Physically Faithful Volumetric Models of Partially Translucent Objects](https://mlsanity.com/paper/2312.13494/) (2023)

## Abstract (arXiv)

We introduce inverse transport networks as a learning architecture for inverse rendering problems where, given input image measurements, we seek to infer physical scene parameters such as shape, material, and illumination. During training, these networks are evaluated not only in terms of how close they can predict groundtruth parameters, but also in terms of whether the parameters they produce can be used, together with physically-accurate graphics renderers, to reproduce the input image measurements. To en- able training of inverse transport networks using stochastic gradient descent, we additionally create a general-purpose, physically-accurate differentiable renderer, which can be used to estimate derivatives of images with respect to arbitrary physical scene parameters. Our experiments demonstrate that inverse transport networks can be trained efficiently using differentiable rendering, and that they generalize to scenes with completely unseen geometry and illumination better than networks trained without appearance- matching regularization.