# Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

arXiv: https://arxiv.org/abs/1806.01911 · HTML: https://mlsanity.com/paper/1806.01911/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2018.

## Built on by (most cited first, 27 of 27)

- [NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing](https://mlsanity.com/paper/2207.11911/) (2022)
- [PD-GAN: Probabilistic Diverse GAN for Image Inpainting](https://mlsanity.com/paper/2105.02201/) (2021)
- [Editing a classifier by rewriting its prediction rules](https://mlsanity.com/paper/2112.01008/) (2021)
- [Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training](https://mlsanity.com/paper/2111.01118/) (2021)
- [Robust Visual Question Answering: Datasets, Methods, and Future Challenges](https://mlsanity.com/paper/2307.11471/) (2023)
- [Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields](https://mlsanity.com/paper/2307.15131/) (2023)
- [High-Fidelity Image Inpainting with GAN Inversion](https://mlsanity.com/paper/2208.11850/) (2022)
- [Weakly-supervised Contrastive Learning for Unsupervised Object Discovery](https://mlsanity.com/paper/2307.03376/) (2023)
- [Unbiased Multi-Modality Guidance for Image Inpainting](https://mlsanity.com/paper/2208.11844/) (2022)
- [Fast Sun-aligned Outdoor Scene Relighting based on TensoRF](https://mlsanity.com/paper/2311.03965/) (2023)
- [Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow](https://mlsanity.com/paper/2201.05723/) (2022)
- [DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection](https://mlsanity.com/paper/2203.09121/) (2022)
- [One-Shot Video Inpainting](https://mlsanity.com/paper/2302.14362/) (2023)
- [SplatMesh: Interactive 3D Segmentation and Editing Using Mesh-Based Gaussian Splatting](https://mlsanity.com/paper/2312.15856/) (2023)
- [Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection](https://mlsanity.com/paper/2212.05667/) (2022)
- [DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder](https://mlsanity.com/paper/2111.03480/) (2021)
- [Instance-Aware Image Completion](https://mlsanity.com/paper/2210.12350/) (2022)
- [Target-Free Text-guided Image Manipulation](https://mlsanity.com/paper/2211.14544/) (2022)
- [Inpainting-Driven Mask Optimization for Object Removal](https://mlsanity.com/paper/2403.15849/) (2024)
- [Enabling Privacy-Aware AI-Based Ergonomic Analysis](https://mlsanity.com/paper/2505.07306/) (2025)
- [Improve Deep Image Inpainting by Emphasizing the Complexity of Missing Regions](https://mlsanity.com/paper/2202.06266/) (2022)
- [Mask-Guided Image Person Removal with Data Synthesis](https://mlsanity.com/paper/2209.14890/) (2022)
- [Task-Decoupled Image Inpainting Framework for Class-specific Object Remover](https://mlsanity.com/paper/2410.02894/) (2024)
- [Improving Detail in Pluralistic Image Inpainting with Feature Dequantization](https://mlsanity.com/paper/2412.01046/) (2024)
- [High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion](https://mlsanity.com/paper/2504.12844/) (2025)
- [Privacy-Preserving Computer Vision for Industry: Three Case Studies in Human-Centric Manufacturing](https://mlsanity.com/paper/2512.09463/) (2025)
- [NeuMesh++: Towards Versatile and Efficient Volumetric Editing with Disentangled Neural Mesh-based Implicit Field](https://mlsanity.com/paper/2606.19316/) (2026)

## Abstract (arXiv)

While great progress has been made recently in automatic image manipulation, it has been limited to object centric images like faces or structured scene datasets. In this work, we take a step towards general scene-level image editing by developing an automatic interaction-free object removal model. Our model learns to find and remove objects from general scene images using image-level labels and unpaired data in a generative adversarial network (GAN) framework. We achieve this with two key contributions: a two-stage editor architecture consisting of a mask generator and image in-painter that co-operate to remove objects, and a novel GAN based prior for the mask generator that allows us to flexibly incorporate knowledge about object shapes. We experimentally show on two datasets that our method effectively removes a wide variety of objects using weak supervision only