dissertation · Digital Repository (National Repository of Grey Literature) · 2026

Distributed differentiable rendering for Mitsuba 3

Cited by 0Abstract and details only

Abstract

Mitsuba 3 is a research-oriented renderer capable of auto-differentiation and inverse rendering. It currently runs on a single CPU or GPU, hence unable to take advantage of distributed computing or multi-gpu systems. Our work provides a library that overcomes this constraint, allowing both the forward rendering and differentiable rendering to occur on a cluster of machines or multiple GPUs on a single machine. This is exposed to the user using an API similar to that of base Mitsuba. We have also implemented adaptive image-space sampling, allowing the renderer to preferrably spend computational resources on demanding regions of the image, which leads to less noisy images at a fixed computation time compared to traditional rendering.

Cite this paper

APA 7

Pelc, J. (2026). Distributed differentiable rendering for Mitsuba 3. Digital Repository (National Repository of Grey Literature).

MLA 9

Pelc, Jakub. “Distributed differentiable rendering for Mitsuba 3.” Digital Repository (National Repository of Grey Literature), 2026.

Chicago

Pelc, Jakub. 2026. “Distributed differentiable rendering for Mitsuba 3.” Digital Repository (National Repository of Grey Literature).

Harvard

Pelc, J. (2026) ‘Distributed differentiable rendering for Mitsuba 3’, Digital Repository (National Repository of Grey Literature).

BibTeX

@phdthesis{pelc2026distributed,
  title = {{Distributed differentiable rendering for Mitsuba 3}},
  author = {Pelc, Jakub},
  school = {Digital Repository (National Repository of Grey Literature)},
  year = {2026}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.