# BlendTorch: A Real-Time, Adaptive Domain Randomization Library

arXiv: https://arxiv.org/abs/2010.11696 · HTML: https://mlsanity.com/paper/2010.11696/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [3DB: A Framework for Debugging Computer Vision Models](https://mlsanity.com/paper/2106.03805/) (2021)
- [PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision](https://mlsanity.com/paper/2112.09290/) (2021)
- [Close the Sim2real Gap via Physically-based Structured Light Synthetic Data Simulation](https://mlsanity.com/paper/2407.12449/) (2024)
- [Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap](https://mlsanity.com/paper/2203.03833/) (2022)
- [WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users](https://mlsanity.com/paper/2404.17063/) (2024)
- [Bag of Views: An Appearance-based Approach to Next-Best-View Planning for 3D Reconstruction](https://mlsanity.com/paper/2307.05832/) (2023)
- [Blazer: Laser Scanning Simulation using Physically Based Rendering](https://mlsanity.com/paper/2104.05430/) (2021)
- [SynthRender and I-AsSET: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception](https://mlsanity.com/paper/2602.21141/) (2026)
- [Visual Deformation Detection Using Soft Material Simulation for Pre-training of Condition Assessment Models](https://mlsanity.com/paper/2405.14877/) (2024)
- [Sim-to-Real Domain Adaptation for Deformation Classification](https://mlsanity.com/paper/2407.10011/) (2024)

## Abstract (arXiv)

Solving complex computer vision tasks by deep learning techniques relies on large amounts of (supervised) image data, typically unavailable in industrial environments. The lack of training data starts to impede the successful transfer of state-of-the-art methods in computer vision to industrial applications. We introduce BlendTorch, an adaptive Domain Randomization (DR) library, to help creating infinite streams of synthetic training data. BlendTorch generates data by massively randomizing low-fidelity simulations and takes care of distributing artificial training data for model learning in real-time. We show that models trained with BlendTorch repeatedly perform better in an industrial object detection task than those trained on real or photo-realistic datasets.