In this paper, we present RayTracer.jl, a renderer in Julia that is fully differentiable using source-to-source Automatic Differentiation (AD). This means that RayTracer not only renders 2D images from 3D scene parameters, but it can be used to optimize for model parameters that generate a target image in a Differentiable Programming (DP) pipeline. We interface our renderer with the deep learning library Flux for use in combination with neural networks. We demonstrate the use of this differentiable renderer in rendering tasks and in solving inverse graphics problems.
RayTracer.jl: A Differentiable Renderer that supports Parameter Optimization for Scene Reconstruction
A differentiable ray tracer in Julia interfaces with Flux for optimizing model parameters in rendering and solving inverse graphics problems.
- Year
- 2019
- Venue
- arXiv 2019
- Authors
- 1
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/1907.07198v3ARXIV-DEFAULT
- TL;DR
- Semantic Scholar