Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking

• URL: http://arxiv.org/abs/2605.25568v1
• Date: Mon, 25 May 2026 08:20:23 GMT
• Title: Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking
• Abstract summary: Scribble-guided image editing allows users to combine simple scribble annotations with text prompts to specify both where and how an image should be edited.<n>Existing models still exhibit unstable performance under this paradigm, especially in multi-task scenarios.<n>We conduct empirical studies using an open-source editing model and reveal an asymmetry in generalization.
• Score: 14.173267480504842
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scribble-guided image editing allows users to combine simple scribble annotations with text prompts to specify both where and how an image should be edited, enabling flexible interaction with precise spatial control. However, existing models still exhibit unstable performance under this paradigm, especially in multi-task scenarios. To improve performance, we conduct empirical studies using an open-source editing model and reveal an asymmetry in generalization: instruction-level generalization, including across editing tasks and from single-task to multi-task settings, is more challenging than image-domain generalization, such as from synthetic to real-world images or from mosaicked to regular images. This suggests that the primary bottleneck lies in insufficient learning for diverse editing instructions rather than in the image domain gap. Motivated by this insight, we propose three strategies: (a) a Coverage-then-Realism Curriculum, a two-stage pipeline that first builds large-scale synthetic, instruction-rich data for broad task supervision, then curates a small set of real-world data to refine generation realism; (b) Multi-Task Mosaicking, which constructs multi-task training samples by concatenating single-task examples at nearly zero cost while enabling the learned capability to generalize to non-mosaicked images; and (c) an Edit-Focused Loss, which leverages the changed regions between input and output images in synthetic data to focus training on edited regions, improving both learning efficiency and editing accuracy. With these strategies, we substantially improve both single-task and multi-task scribble-guided editing on the VIBE benchmark, achieving state-of-the-art results. We will publicly release our dataset and model.

Related papers

• Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning [43.870883813242166]
  We propose Uni-Edit, an intelligent image editing task that serves as the first general task for Unified Multimodal Models tuning.<n>Unlike complex mixed pipelines, Uni-Edit improves performance across all three abilities at once using only one task, one training stage, and one dataset.<n>We show that tuning solely on Uni-Edit achieves comprehensive enhancements across all three capabilities without any auxiliary operations.
  arXiv  Detail & Related papers  (2026-05-20T17:59:42Z)
• WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing [103.68419705566146]
  We present WeEdit, a systematic solution encompassing a scalable data construction pipeline, two benchmarks, and a tailored two-stage training strategy.<n>Specifically, we propose a novel HTML-based automatic editing pipeline, which generates 330K training pairs covering diverse editing operations and 15 languages.<n>On the algorithmic side, we employ glyph-guided supervised fine-tuning to inject explicit spatial and content priors, followed by a multi-objective reinforcement learning stage to align generation with instruction adherence, text clarity, and background preservation.
  arXiv  Detail & Related papers  (2026-03-12T06:25:09Z)
• ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning [20.61925053714293]
  Image editing systems often struggle with complex, indirect, or multi-step user instructions.<n>We propose ImageEdit-R1, a multi-agent framework for intelligent image editing.<n>Our method treats image editing as a sequential decision-making problem, enabling dynamic and context-aware editing strategies.
  arXiv  Detail & Related papers  (2026-03-09T07:50:14Z)
• UniREditBench: A Unified Reasoning-based Image Editing Benchmark [52.54256348710893]
  This work proposes UniREditBench, a unified benchmark for reasoning-based image editing evaluation.<n>It comprises 2,700 meticulously curated samples, covering both real- and game-world scenarios across 8 primary dimensions and 18 sub-dimensions.<n>We fine-tune Bagel on this dataset and develop UniREdit-Bagel, demonstrating substantial improvements in both in-domain and out-of-distribution settings.
  arXiv  Detail & Related papers  (2025-11-03T07:24:57Z)
• Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions [20.617718631292696]
  We develop a novel paradigm for instruction-driven image editing that leverages widely available and enormous text-image pairs.<n>Our approach introduces a multi-scale learnable region to localize and guide the editing process.<n>By treating the alignment between images and their textual descriptions as supervision and learning to generate task-specific editing regions, our method achieves high-fidelity, precise, and instruction-consistent image editing.
  arXiv  Detail & Related papers  (2025-05-25T22:40:59Z)
• SPIE: Semantic and Structural Post-Training of Image Editing Diffusion Models with AI feedback [28.807572302899004]
  SPIE is a novel approach for semantic and structural post-training of instruction-based image editing diffusion models.<n>We introduce an online reinforcement learning framework that aligns the diffusion model with human preferences without relying on extensive human annotations.<n> Experimental results demonstrate that SPIE can perform intricate edits in complex scenes, after just 10 training steps.
  arXiv  Detail & Related papers  (2025-04-17T10:46:39Z)
• Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing [60.730661748555214]
  We introduce textbfTask-textbfOriented textbfDiffusion textbfInversion (textbfTODInv), a novel framework that inverts and edits real images tailored to specific editing tasks. ToDInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability.
  arXiv  Detail & Related papers  (2024-08-23T22:16:34Z)
• A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models [117.77807994397784]
  Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. Recent significant advancement in this field is based on the development of text-to-image (T2I) diffusion models. T2I-based image editing methods significantly enhance editing performance and offer a user-friendly interface for modifying content guided by multimodal inputs.
  arXiv  Detail & Related papers  (2024-06-20T17:58:52Z)
• Emu Edit: Precise Image Editing via Recognition and Generation Tasks [62.95717180730946]
  We present Emu Edit, a multi-task image editing model which sets state-of-the-art results in instruction-based image editing. We train it to multi-task across an unprecedented range of tasks, such as region-based editing, free-form editing, and Computer Vision tasks. We show that Emu Edit can generalize to new tasks, such as image inpainting, super-resolution, and compositions of editing tasks, with just a few labeled examples.
  arXiv  Detail & Related papers  (2023-11-16T18:55:58Z)
• Learning by Planning: Language-Guided Global Image Editing [53.72807421111136]
  We develop a text-to-operation model to map the vague editing language request into a series of editing operations. The only supervision in the task is the target image, which is insufficient for a stable training of sequential decisions. We propose a novel operation planning algorithm to generate possible editing sequences from the target image as pseudo ground truth.
  arXiv  Detail & Related papers  (2021-06-24T16:30:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.