# Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation

arXiv: https://arxiv.org/abs/2605.13122 · HTML: https://mlsanity.com/paper/2605.13122/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 52 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [UltraEdit: Instruction-based Fine-Grained Image Editing at Scale](https://mlsanity.com/paper/2407.05282/) (2024)
- [Segmentation from Natural Language Expressions](https://mlsanity.com/paper/1603.06180/) (2016)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea](https://mlsanity.com/paper/2411.15738/) (2024)
- [In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer](https://mlsanity.com/paper/2504.20690/) (2025)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.02664/) (2022)
- [FreeSOLO: Learning to Segment Objects without Annotations](https://mlsanity.com/paper/2202.12181/) (2022)
- [LongCat-Image Technical Report](https://mlsanity.com/paper/2512.07584/) (2025)
- [Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2312.12470/) (2023)
- [CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor](https://mlsanity.com/paper/2312.07661/) (2023)
- [Zero-shot Referring Image Segmentation with Global-Local Context Features](https://mlsanity.com/paper/2303.17811/) (2023)

## Built on by (most cited first, 1 of 1)

- [ContourVLA: A Closed-Loop Perception-Action Contour Policy for Generalized Referring Expression Segmentation](https://mlsanity.com/paper/2610.12107/) (2026)

## Abstract (arXiv)

Instruction-based image editing (IIE) models have recently demonstrated strong capability in modifying specific image regions according to natural language instructions, which implicitly requires identifying where an edit should be applied. This indicates that such models inherently perform language-conditioned visual semantic grounding. In this work, we investigate whether this implicit grounding can be leveraged for zero-shot referring image segmentation (RIS), a task that requires pixel-level localization of objects described by natural language expressions. Through systematic analysis, we reveal that strong foreground-background separability emerges in the internal representations of these models at the earliest denoising timestep, well before any visible image transformation occurs. Building on this insight, we propose a training-free framework that repurposes pretrained image editing models for RIS by exploiting their intermediate representations. Our approach decomposes localization into two complementary components: attention-based spatial priors that estimate where to focus, and feature-based semantic discrimination that determines what to segment. By leveraging feature-space separability, the framework produces accurate segmentation masks using only a single denoising step, without requiring full image synthesis. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg demonstrate that our method achieves superior performance over existing zero-shot baselines.