# Image Shape Manipulation from a Single Augmented Training Sample

arXiv: https://arxiv.org/abs/2007.01289 · HTML: https://mlsanity.com/paper/2007.01289/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2020.

## Built on by (most cited first, 13 of 13)

- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [Dreamix: Video Diffusion Models are General Video Editors](https://mlsanity.com/paper/2302.01329/) (2023)
- [EpiGRAF: Rethinking training of 3D GANs](https://mlsanity.com/paper/2206.10535/) (2022)
- [Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models](https://mlsanity.com/paper/2305.04441/) (2023)
- [ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation](https://mlsanity.com/paper/2308.00906/) (2023)
- [LogicAL: Towards logical anomaly synthesis for unsupervised anomaly localization](https://mlsanity.com/paper/2405.06875/) (2024)
- [FreeInv: Free Lunch for Improving DDIM Inversion](https://mlsanity.com/paper/2503.23035/) (2025)
- [MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier](https://mlsanity.com/paper/2209.11549/) (2022)
- [ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions](https://mlsanity.com/paper/2205.12231/) (2022)
- [CustomSketching: Sketch Concept Extraction for Sketch-based Image Synthesis and Editing](https://mlsanity.com/paper/2402.17624/) (2024)
- [AnomalyFactory: Regard Anomaly Generation as Unsupervised Anomaly Localization](https://mlsanity.com/paper/2408.09533/) (2024)
- [AnomalyHybrid: A Domain-agnostic Generative Framework for General Anomaly Detection](https://mlsanity.com/paper/2504.04340/) (2025)
- [Active Generation Network of Human Skeleton for Action Recognition](https://mlsanity.com/paper/2401.17086/) (2024)

## Abstract (arXiv)

In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network. Our method is shown to achieve remarkable performance on image manipulation tasks.