Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing
- URL: http://arxiv.org/abs/2606.05172v1
- Date: Thu, 16 Apr 2026 08:05:42 GMT
- Title: Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing
- Abstract summary: Diffusion-based image editing has achieved strong visual fidelity under natural language instructions.<n>Most existing systems still operate at the level of surface instruction following, without reasoning about the implicit contextual constraints.<n>We introduce RE-Edit, a benchmark for REasoning-aware image editing.
- Score: 45.07920210103563
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Diffusion-based image editing has achieved strong visual fidelity under natural language instructions, yet most existing systems still operate at the level of surface instruction following, without reasoning about the implicit contextual constraints embedded in real user requests. This often leads to visually plausible but logically inconsistent edits. In this work, we introduce RE-Edit, a benchmark for REasoning-aware image Editing that evaluates image editing systems across five complementary reasoning dimensions: physical, environmental, cultural, causal, and referential. RE-Edit comprises 1,000 carefully curated samples, each designed such that visual plausibility alone is insufficient and correct editing requires satisfying implicit logical constraints. To support fine-grained analysis, we establish dimension-aligned evaluation criteria and conduct a comprehensive study of ten open-source and two commercial image editing models. Our results show that even advanced systems frequently struggle with implicit multi-dimensional reasoning despite producing high-quality visuals. We further present a lightweight reasoning-guided post-edit baseline as an initial exploration, illustrating how inserting explicit reasoning can help mitigate such failures in a model-agnostic manner.
Related papers
- ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning [86.61218827780675]
We present ReasonEdit, an evaluation tool for text-guided image editing.<n>It is trained using reward signals derived from RE-Reward and the Group Relative Policy Optimization (GRPO) algorithm.<n>It is capable of generating high-quality interpretable evaluation text, enabling more transparent and trustworthy assessment for image editing.
arXiv Detail & Related papers (2026-05-08T09:23:26Z) - EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement [76.76247443244293]
EditRefiner is an agentic framework that reformulates post-editing correction as a human-like perception-reasoning-action-evaluation loop.<n>It consistently outperforms state-of-the-art methods in distortion, diagnose accuracy and human perception alignment.
arXiv Detail & Related papers (2026-05-08T09:05:08Z) - CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator [8.901958956012072]
Conditional image editing is crucial in scenarios requiring strict structural control.<n>Most approaches rely on single-step generation.<n>We propose textbfCAMEO, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process.
arXiv Detail & Related papers (2026-04-03T16:27:02Z) - ReViSE: Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning [57.08352504712699]
Video unified models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing.<n>We introduce the Reason-Informed Video Editing (RVE) task, which requires reasoning about physical plausibility and causal dynamics during editing.<n>We propose ReViSE, a framework that unifies generation and evaluation within a single architecture.
arXiv Detail & Related papers (2025-12-10T18:57:09Z) - Charts Are Not Images: On the Challenges of Scientific Chart Editing [66.38730113476677]
textitFigEdit is a benchmark for scientific figure editing comprising over 30,000 samples.<n>Our benchmark demonstrates the profound limitations of pixel-level manipulation.<n>By releasing textitFigEdit, we aim to enable systematic progress in structure-aware figure editing.
arXiv Detail & Related papers (2025-11-30T06:13:48Z) - Understanding the Implicit User Intention via Reasoning with Large Language Model for Image Editing [23.69189799564107]
Existing image editing methods can handle simple editing instructions very well.<n>To deal with complex editing instructions, they often need to jointly fine-tune the large language models (LLMs) and diffusion models (DMs)<n>We propose a new method, called textbfComplex textbfImage textbfEditing via textbfLLM textbfReasoning (CIELR), which converts a complex user instruction into a set of simple and explicit editing actions.
arXiv Detail & Related papers (2025-10-31T10:06:28Z) - SpotEdit: Evaluating Visually-Guided Image Editing Methods [3.5066378196008636]
SpotEdit is a comprehensive benchmark designed to assess visually-guided image editing methods.<n>Our benchmark includes a dedicated component on hallucination, highlighting how leading models, such as GPT-4o, often hallucinate the existence of a visual cue and erroneously perform the editing task.
arXiv Detail & Related papers (2025-08-25T16:08:57Z) - Concept Lancet: Image Editing with Compositional Representation Transplant [58.9421919837084]
Concept Lancet is a zero-shot plug-and-play framework for principled representation manipulation in image editing.<n>We decompose the source input in the latent (text embedding or diffusion score) space as a sparse linear combination of the representations of the collected visual concepts.<n>We perform a customized concept transplant process to impose the corresponding editing direction.
arXiv Detail & Related papers (2025-04-03T17:59:58Z)
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.