Paper Detail

Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo

Zeyu Ma, Alexander Raistrick, Jia Deng

arxiv Score 3.8

Published 2026-04-06 · First seen 2026-04-07

General AI

Abstract

In this paper, we explore the design space of procedural rules for multi-view stereo (MVS). We demonstrate that we can generate effective training data using SimpleProc: a new, fully procedural generator driven by a very small set of rules using Non-Uniform Rational Basis Splines (NURBS), as well as basic displacement and texture patterns. At a modest scale of 8,000 images, our approach achieves superior results compared to manually curated images (at the same scale) sourced from games and real-world objects. When scaled to 352,000 images, our method yields performance comparable to--and in several benchmarks, exceeding--models trained on over 692,000 manually curated images. The source code and the data are available at https://github.com/princeton-vl/SimpleProc.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{ma2026fully,
  title = {Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo},
  author = {Zeyu Ma and Alexander Raistrick and Jia Deng},
  year = {2026},
  abstract = {In this paper, we explore the design space of procedural rules for multi-view stereo (MVS). We demonstrate that we can generate effective training data using SimpleProc: a new, fully procedural generator driven by a very small set of rules using Non-Uniform Rational Basis Splines (NURBS), as well as basic displacement and texture patterns. At a modest scale of 8,000 images, our approach achieves superior results compared to manually curated images (at the same scale) sourced from games and real-},
  url = {https://arxiv.org/abs/2604.04925},
  keywords = {cs.CV},
  eprint = {2604.04925},
  archiveprefix = {arXiv},
}

Metadata

{}