# Inverse Scene Text Removal

arXiv: https://arxiv.org/abs/2506.21002 · HTML: https://mlsanity.com/paper/2506.21002/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 24 of 24)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [TextBoxes: A Fast Text Detector with a Single Deep Neural Network](https://mlsanity.com/paper/1611.06779/) (2016)
- [TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://mlsanity.com/paper/1807.01544/) (2018)
- [Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis](https://mlsanity.com/paper/2303.10762/) (2023)
- [CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model](https://mlsanity.com/paper/2305.14014/) (2023)
- [MTRNet: A Generic Scene Text Eraser](https://mlsanity.com/paper/1903.04092/) (2019)
- [Arbitrary Shape Text Detection via Boundary Transformer](https://mlsanity.com/paper/2205.05320/) (2022)
- [EnsNet: Ensconce Text in the Wild](https://mlsanity.com/paper/1812.00723/) (2018)
- [Scene Text Eraser](https://mlsanity.com/paper/1705.02772/) (2017)
- [De-rendering Stylized Texts](https://mlsanity.com/paper/2110.01890/) (2021)
- [ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining](https://mlsanity.com/paper/2306.12106/) (2023)
- [Automatic Semantic Content Removal by Learning to Neglect](https://mlsanity.com/paper/1807.07696/) (2018)
- [DeepEraser: Deep Iterative Context Mining for Generic Text Eraser](https://mlsanity.com/paper/2402.19108/) (2024)
- [Selective Scene Text Removal](https://mlsanity.com/paper/2309.00410/) (2023)

## Abstract (arXiv)

Scene text removal (STR) aims to erase textual elements from images. It was originally intended for removing privacy-sensitiveor undesired texts from natural scene images, but is now also appliedto typographic images. STR typically detects text regions and theninpaints them. Although STR has advanced through neural networksand synthetic data, misuse risks have increased. This paper investi-gates Inverse STR (ISTR), which analyzes STR-processed images andfocuses on binary classification (detecting whether an image has un-dergone STR) and localizing removed text regions. We demonstrate inexperiments that these tasks are achievable with high accuracies, en-abling detection of potential misuse and improving STR. We also at-tempt to recover the removed text content by training a text recognizerto understand its difficulty.