# ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion

arXiv: https://arxiv.org/abs/2403.18818 · HTML: https://mlsanity.com/paper/2403.18818/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 53 of its 64 references that are in the map.
- First posted on arXiv 27 Mar 2024.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 53)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Variational Autoencoders and Nonlinear ICA: A Unifying Framework](https://mlsanity.com/paper/1907.04809/) (2019)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [Emu Edit: Precise Image Editing via Recognition and Generation Tasks](https://mlsanity.com/paper/2311.10089/) (2023)
- [Text2LIVE: Text-Driven Layered Image and Video Editing](https://mlsanity.com/paper/2204.02491/) (2022)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [Guiding Instruction-based Image Editing via Multimodal Large Language Models](https://mlsanity.com/paper/2309.17102/) (2023)
- [HIVE: Harnessing Human Feedback for Instructional Visual Editing](https://mlsanity.com/paper/2303.09618/) (2023)

## Built on by (most cited first, 30 of 71)

- [OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting](https://mlsanity.com/paper/2503.08677/) (2025)
- [Generative Omnimatte: Learning to Decompose Video into Layers](https://mlsanity.com/paper/2411.16683/) (2024)
- [OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data](https://mlsanity.com/paper/2501.07397/) (2025)
- [Generative Image Layer Decomposition with Visual Effects](https://mlsanity.com/paper/2411.17864/) (2024)
- [NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining](https://mlsanity.com/paper/2507.14119/) (2025)
- [ObjectMover: Generative Object Movement with Video Prior](https://mlsanity.com/paper/2503.08037/) (2025)
- [SmartEraser: Remove Anything from Images using Masked-Region Guidance](https://mlsanity.com/paper/2501.08279/) (2025)
- [RORem: Training a Robust Object Remover with Human-in-the-Loop](https://mlsanity.com/paper/2501.00740/) (2025)
- [DiffUHaul: A Training-Free Method for Object Dragging in Images](https://mlsanity.com/paper/2406.01594/) (2024)
- [CLIPAway: Harmonizing Focused Embeddings for Removing Objects via Diffusion Models](https://mlsanity.com/paper/2406.09368/) (2024)
- [PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models](https://mlsanity.com/paper/2503.10127/) (2025)
- [R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation](https://mlsanity.com/paper/2506.07826/) (2025)
- [Magic Insert: Style-Aware Drag-and-Drop](https://mlsanity.com/paper/2407.02489/) (2024)
- [Generative AI for Cel-Animation: A Survey](https://mlsanity.com/paper/2501.06250/) (2025)
- [IntrinsicEdit: Precise generative image manipulation in intrinsic space](https://mlsanity.com/paper/2505.08889/) (2025)
- [Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections](https://mlsanity.com/paper/2409.14677/) (2024)
- [ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation](https://mlsanity.com/paper/2412.08645/) (2024)
- [OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models](https://mlsanity.com/paper/2503.18033/) (2025)
- [EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing](https://mlsanity.com/paper/2603.19224/) (2026)
- [VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors](https://mlsanity.com/paper/2503.01107/) (2025)
- [DreamFuse: Adaptive Image Fusion with Diffusion Transformer](https://mlsanity.com/paper/2504.08291/) (2025)
- [Precise Object and Effect Removal with Adaptive Target-Aware Attention](https://mlsanity.com/paper/2505.22636/) (2025)
- [Learning an Image Editing Model without Image Editing Pairs](https://mlsanity.com/paper/2510.14978/) (2025)
- [3D-Fixup: Advancing Photo Editing with 3D Priors](https://mlsanity.com/paper/2505.10566/) (2025)
- [Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting](https://mlsanity.com/paper/2503.21770/) (2025)
- [ORIDa: Object-centric Real-world Image Composition Dataset](https://mlsanity.com/paper/2506.08964/) (2025)
- [Group Editing: Edit Multiple Images in One Go](https://mlsanity.com/paper/2603.22883/) (2026)
- [DynVFX: Augmenting Real Videos with Dynamic Content](https://mlsanity.com/paper/2502.03621/) (2025)
- [Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy](https://mlsanity.com/paper/2506.22432/) (2025)
- [GeoRemover: Removing Objects and Their Causal Visual Artifacts](https://mlsanity.com/paper/2509.18538/) (2025)

## Abstract (arXiv)

Diffusion models have revolutionized image editing but often generate images that violate physical laws, particularly the effects of objects on the scene, e.g., occlusions, shadows, and reflections. By analyzing the limitations of self-supervised approaches, we propose a practical solution centered on a qcounterfactual dataset. Our method involves capturing a scene before and after removing a single object, while minimizing other changes. By fine-tuning a diffusion model on this dataset, we are able to not only remove objects but also their effects on the scene. However, we find that applying this approach for photorealistic object insertion requires an impractically large dataset. To tackle this challenge, we propose bootstrap supervision; leveraging our object removal model trained on a small counterfactual dataset, we synthetically expand this dataset considerably. Our approach significantly outperforms prior methods in photorealistic object removal and insertion, particularly at modeling the effects of objects on the scene.