# GeoRemover: Removing Objects and Their Causal Visual Artifacts

arXiv: https://arxiv.org/abs/2509.18538 · HTML: https://mlsanity.com/paper/2509.18538/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 51 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 30 of 38)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [Emu Edit: Precise Image Editing via Recognition and Generation Tasks](https://mlsanity.com/paper/2311.10089/) (2023)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model](https://mlsanity.com/paper/2212.05034/) (2022)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion](https://mlsanity.com/paper/2403.06976/) (2024)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)
- [Learning Multi-dimensional Human Preference for Text-to-Image Generation](https://mlsanity.com/paper/2405.14705/) (2024)
- [ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion](https://mlsanity.com/paper/2403.18818/) (2024)
- [Image Inpainting via Conditional Texture and Structure Dual Generation](https://mlsanity.com/paper/2108.09760/) (2021)
- [Inst-Inpaint: Instructing to Remove Objects with Diffusion Models](https://mlsanity.com/paper/2304.03246/) (2023)
- [Zero-shot Image Editing with Reference Imitation](https://mlsanity.com/paper/2406.07547/) (2024)
- [Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance](https://mlsanity.com/paper/2412.12974/) (2024)
- [Designing a Better Asymmetric VQGAN for StableDiffusion](https://mlsanity.com/paper/2306.04632/) (2023)
- [WaveFill: A Wavelet-based Generation Network for Image Inpainting](https://mlsanity.com/paper/2107.11027/) (2021)
- [Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting](https://mlsanity.com/paper/2403.19898/) (2024)

## Built on by (most cited first, 9 of 9)

- [From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition](https://mlsanity.com/paper/2511.20996/) (2025)
- [FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching](https://mlsanity.com/paper/2605.09003/) (2026)
- [DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver](https://mlsanity.com/paper/2605.30045/) (2026)
- [DORS: Dynamic Attention Routing for Diffusion-based Object Removal in Dense Scenes](https://mlsanity.com/paper/2607.16656/) (2026)
- [BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal](https://mlsanity.com/paper/2608.20107/) (2026)
- [You Only Erase Once: Erasing Anything without Bringing Unexpected Content](https://mlsanity.com/paper/2603.27599/) (2026)
- [DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents](https://mlsanity.com/paper/2605.01789/) (2026)
- [TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion](https://mlsanity.com/paper/2608.01288/) (2026)
- [VOR-Bench: A Human Perception-Driven Benchmark for Video Object Removal](https://mlsanity.com/paper/2609.16878/) (2026)

## Abstract (arXiv)

Towards intelligent image editing, object removal should eliminate both the target object and its causal visual artifacts, such as shadows and reflections. However, existing image appearance-based methods either follow strictly mask-aligned training and fail to remove these causal effects which are not explicitly masked, or adopt loosely mask-aligned strategies that lack controllability and may unintentionally over-erase other objects. We identify that these limitations stem from ignoring the causal relationship between an object's geometry presence and its visual effects. To address this limitation, we propose a geometry-aware two-stage framework that decouples object removal into (1) geometry removal and (2) appearance rendering. In the first stage, we remove the object directly from the geometry (e.g., depth) using strictly mask-aligned supervision, enabling structure-aware editing with strong geometric constraints. In the second stage, we render a photorealistic RGB image conditioned on the updated geometry, where causal visual effects are considered implicitly as a result of the modified 3D geometry. To guide learning in the geometry removal stage, we introduce a preference-driven objective based on positive and negative sample pairs, encouraging the model to remove objects as well as their causal visual artifacts while avoiding new structural insertions. Extensive experiments demonstrate that our method achieves state-of-the-art performance in removing both objects and their associated artifacts on two popular benchmarks. The code is available at https://github.com/buxiangzhiren/GeoRemover.