MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing

• URL: http://arxiv.org/abs/2604.05180v1
• Date: Mon, 06 Apr 2026 21:20:00 GMT
• Title: MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing
• Abstract summary: We observe that state-of-the-art models suffer from severe over-editing and spatial misalignment when faced with multiple identical instances and composite instructions.<n>We propose Multi-Instance Regional Alignment via Guided Editing (MIRAGE), a training-free framework that enables precise, localized editing.<n>Our framework significantly outperforms existing methods in achieving precise instance-level modifications while preserving background consistency.
• Score: 9.297700134159916
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Instruction-guided image editing has seen remarkable progress with models like FLUX.2 and Qwen-Image-Edit, yet they still struggle with complex scenarios with multiple similar instances each requiring individual edits. We observe that state-of-the-art models suffer from severe over-editing and spatial misalignment when faced with multiple identical instances and composite instructions. To this end, we introduce a comprehensive benchmark specifically designed to evaluate fine-grained consistency in multi-instance and multi-instruction settings. To address the failures of existing methods observed in our benchmark, we propose Multi-Instance Regional Alignment via Guided Editing (MIRAGE), a training-free framework that enables precise, localized editing. By leveraging a vision-language model to parse complex instructions into regional subsets, MIRAGE employs a multi-branch parallel denoising strategy. This approach injects latent representations of target regions into the global representation space while maintaining background integrity through a reference trajectory. Extensive evaluations on MIRA-Bench and RefEdit-Bench demonstrate that our framework significantly outperforms existing methods in achieving precise instance-level modifications while preserving background consistency. Our benchmark and code are available at https://github.com/ZiqianLiu666/MIRAGE.

Related papers

• PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation [12.227797182463611]
  We introduce PR-MaGIC (Prompt Refinement via Mask Decoder for In-Context), a training-free test-time framework that refines prompts via gradient flow from SAM's mask decoder.<n> PR-MaGIC consistently improves segmentation quality across various benchmarks, effectively mitigating inadequate prompts without requiring additional training or architectural modifications.
  arXiv  Detail & Related papers  (2026-04-13T22:40:04Z)
• InstanceRSR: Real-World Super-Resolution via Instance-Aware Representation Alignment [6.761263337778605]
  Super-resolution methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions.<n>However, they often struggle to recover fine-grained details of diverse object instances in complex real-world scenes.<n>This limitation primarily arises because commonly adopted denoising losses (e.g., MSE) inherently favor global consistency while neglecting instance-level perception and restoration.
  arXiv  Detail & Related papers  (2026-03-25T12:27:58Z)
• 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)
• The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment [105.31858867473845]
  ImageCritic can be integrated into an agent framework to automatically detect inconsistencies and correct them with multi-round and local editing.<n>In experiments, ImageCritic can effectively resolve detail-related issues in various customized generation scenarios, providing significant improvements over existing methods.
  arXiv  Detail & Related papers  (2025-11-25T18:40:25Z)
• 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)
• RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization [50.75654397516163]
  We propose RelayFormer, a unified framework that adapts to varying resolutions and modalities.<n> RelayFormer partitions inputs into fixed-size sub-images and introduces Global-Local Relay (GLR) tokens.<n>This enables efficient exchange of global cues, such as semantic or temporal consistency, while preserving fine-grained manipulation artifacts.
  arXiv  Detail & Related papers  (2025-08-13T03:35:28Z)
• ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies [13.525744033075785]
  Real-world scenarios often involve complex, multi-step instructions, particularly chain'' instructions where operations are interdependent.<n>Current models struggle with these intricate directives, and existing benchmarks inadequately evaluate such capabilities.<n>We introduce ComplexBench-Edit, a novel benchmark designed to systematically assess model performance on complex, multi-instruction, and chain-dependent image editing tasks.
  arXiv  Detail & Related papers  (2025-06-15T12:22:55Z)
• Image Editing As Programs with Diffusion Models [69.05164729625052]
  We introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture.<n>IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations.<n>Our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions.
  arXiv  Detail & Related papers  (2025-06-04T16:57:24Z)
• CompBench: Benchmarking Complex Instruction-guided Image Editing [63.347846732450364]
  CompBench is a large-scale benchmark for complex instruction-guided image editing.<n>We propose an MLLM-human collaborative framework with tailored task pipelines.<n>We propose an instruction decoupling strategy that disentangles editing intents into four key dimensions.
  arXiv  Detail & Related papers  (2025-05-18T02:30:52Z)
• Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolution [52.55429225242423]
  We propose a novel framework for Burst Image Super-Resolution (BISR), featuring an equivariant convolution-based alignment.<n>This enables the alignment transformation to be learned via explicit supervision in the image domain and easily applied in the feature domain.<n>Experiments on BISR benchmarks show the superior performance of our approach in both quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2025-03-11T11:13:10Z)

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.