Evaluation-Verification Reward for Consistent Multi-Reference Image Editing

• URL: http://arxiv.org/abs/2607.29025v2
• Date: Wed, 05 Aug 2026 10:28:47 GMT
• Title: Evaluation-Verification Reward for Consistent Multi-Reference Image Editing
• Abstract summary: Multi-dimensional Evaluation-Verification Reward(EVR)<n>EVR decomposes evaluation into distinct visual criteria.<n>Verifier grounds each claim in concrete visual evidence to accept or reject it.
• Score: 40.370544121781144
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While recent image editing models have made rapid progress, multi-reference editing remains challenging, particularly in maintaining visual consistency across references and ensuring overall visual harmony. Reinforcement learning has proven highly effective for text-to-image generation and single-image editing, but its extension to multi-reference editing is hindered by the absence of suitable reward models that capture multi-image relational constraints. Moreover, naively using multimodal large language models(MLLMs) as zero-shot evaluators faces a key tension between hallucination-prone long-form reasoning and the limited deductive power of short-form judgments. We address these issues with a Multi-dimensional Evaluation-Verification Reward(EVR). EVR decomposes evaluation into distinct visual criteria; for each criterion, an MLLM Evaluator generates multiple candidate hypotheses, and a Verifier grounds each claim in concrete visual evidence to accept or reject it, producing reliable and fine-grained reward signals. Together with a scalable data pipeline, our method enables RL fine-tuning of off-the-shelf editors without architectural changes. Extensive experiments show substantial gains over the base Qwen-Image-Edit, improving consistency and harmony to match or surpass NanoBanana.

Related papers

• DiffCap-Bench: A Comprehensive, Challenging, Robust Benchmark for Image Difference Captioning [26.88130913151649]
  Image Difference Captioning (IDC) generates language descriptions that precisely identify differences between two images.<n>We introduce DiffCap-Bench, a comprehensive IDC benchmark covering ten distinct difference categories.<n>We also propose an LLM-as-a-Judge evaluation protocol grounded in human-validated Difference Lists.
  arXiv  Detail & Related papers  (2026-05-06T05:12:41Z)
• Enhanced Text-to-Image Generation by Fine-grained Multimodal Reasoning [13.412268665909826]
  Fine-grained Multimodal Reasoning (FiMR) is a framework that leverages visual question answering (VQA) to generate explicit, fine-grained feedback.<n>FiMR consistently outperforms image generation baselines, including reasoning-based methods.
  arXiv  Detail & Related papers  (2026-04-15T05:24:29Z)
• ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models [4.257440824082894]
  We introduce ChartEditBench, a benchmark for incremental, visually grounded chart editing via code.<n>Unlike prior one-shot benchmarks, ChartEditBench evaluates sustained, context-aware editing.<n> Experiments with state-of-the-art MLLMs reveal substantial degradation in multi-turn settings due to error accumulation and breakdowns in shared context.
  arXiv  Detail & Related papers  (2026-02-17T17:45:34Z)
• More Images, More Problems? A Controlled Analysis of VLM Failure Modes [80.64323947730905]
  Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities, yet their proficiency in understanding and reasoning over multiple images remains largely unexplored.<n>We introduce MIMIC, a new benchmark designed to rigorously evaluate the multi-image capabilities of LVLMs.
  arXiv  Detail & Related papers  (2026-01-12T18:45:13Z)
• Towards Generalized Multi-Image Editing for Unified Multimodal Models [56.620038824933566]
  Unified Multimodal Models (UMMs) integrate multimodal understanding and generation.<n>UMMs are limited to maintaining visual consistency and disambiguating visual cues when referencing details across multiple input images.<n>We propose a scalable multi-image editing framework for UMMs that explicitly distinguishes image identities and generalizes to variable input counts.
  arXiv  Detail & Related papers  (2026-01-09T06:42:49Z)
• ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing [33.888289858260706]
  Reinforcement learning (RL) has been investigated for improving the quality of image editing.<n>RL faces three key challenges: (1) limited reasoning exploration confined to denoising, (2) biased reward fusion, and (3) unstable VLM-based instruction rewards.<n>We propose ThinkRL-Edit, a reasoning-centric RL framework that decouples visual reasoning from image synthesis.
  arXiv  Detail & Related papers  (2026-01-06T23:43:00Z)
• CRAFT: Continuous Reasoning and Agentic Feedback Tuning for Multimodal Text-to-Image Generation [0.0]
  CRAFT (Continuous Reasoning and Agentic Feedback Tuning) is a training-free, model-agnostic framework that brings structured reasoning paradigm to multimodal image generation.<n>It consistently improves compositional accuracy, text rendering, and preference-based evaluations.<n>These improvements incur only a negligible inference-time overhead, allowing smaller or cheaper models to approach the quality of substantially more expensive systems.
  arXiv  Detail & Related papers  (2025-12-23T13:44:41Z)
• 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)
• What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models [88.398085358514]
  DICE is a model designed to detect localized differences between the original and the edited image.<n>It is trained using a strategy that leverages self-supervision, distillation from inpainting networks, and full supervision.<n>We demonstrate that DICE effectively identifies coherent edits, effectively evaluating images generated by different editing models with a strong correlation with human judgment.
  arXiv  Detail & Related papers  (2025-05-26T18:00:10Z)
• CoLLM: A Large Language Model for Composed Image Retrieval [76.29725148964368]
  Composed Image Retrieval (CIR) is a complex task that aims to retrieve images based on a multimodal query.<n>We present CoLLM, a one-stop framework that generates triplets on-the-fly from image-caption pairs.<n>We leverage Large Language Models (LLMs) to generate joint embeddings of reference images and modification texts.
  arXiv  Detail & Related papers  (2025-03-25T17:59:50Z)

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.