# Creative synthesis of kinematic mechanisms

arXiv: https://arxiv.org/abs/2510.03308 · HTML: https://mlsanity.com/paper/2510.03308/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](https://mlsanity.com/paper/1703.05192/) (2017)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [Unsupervised Cross-Domain Image Generation](https://mlsanity.com/paper/1611.02200/) (2016)
- [LINKS: A dataset of a hundred million planar linkage mechanisms for data-driven kinematic design](https://mlsanity.com/paper/2208.14567/) (2022)
- [LInK: Learning Joint Representations of Design and Performance Spaces through Contrastive Learning for Mechanism Synthesis](https://mlsanity.com/paper/2405.20592/) (2024)
- [Joint Search of Optimal Topology and Trajectory for Planar Linkages](https://mlsanity.com/paper/2109.03392/) (2021)

## Built on by (most cited first, 1 of 1)

- [Language Models Refine Mechanical Linkage Designs Through Symbolic Reflection and Modular Optimisation](https://mlsanity.com/paper/2604.27962/) (2026)

## Abstract (arXiv)

In this paper, we formulate the problem of kinematic synthesis for planar linkages as a cross-domain image generation task. We develop a planar linkages dataset using RGB image representations, covering a range of mechanisms: from simple types such as crank-rocker and crank-slider to more complex eight-bar linkages like Jansen's mechanism. A shared-latent variational autoencoder (VAE) is employed to explore the potential of image generative models for synthesizing unseen motion curves and simulating novel kinematics. By encoding the drawing speed of trajectory points as color gradients, the same architecture also supports kinematic synthesis conditioned on both trajectory shape and velocity profiles. We validate our method on three datasets of increasing complexity: a standard four-bar linkage set, a mixed set of four-bar and crank-slider mechanisms, and a complex set including multi-loop mechanisms. Preliminary results demonstrate the effectiveness of image-based representations for generative mechanical design, showing that mechanisms with revolute and prismatic joints, and potentially cams and gears, can be represented and synthesized within a unified image generation framework.