CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing

• URL: http://arxiv.org/abs/2603.08589v1
• Date: Mon, 09 Mar 2026 16:40:47 GMT
• Title: CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
• Abstract summary: We propose Condition-Aware of Experts (CARE-Edit) that aligns model computation with specific editing competencies.<n>At its core, a lightweight latent-attention router assigns encoded diffusion tokens to four specialized experts.<n>Experiments validate CARE-Edit's strong performance on contextual editing tasks.
• Score: 17.372230178356357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unified diffusion editors often rely on a fixed, shared backbone for diverse tasks, suffering from task interference and poor adaptation to heterogeneous demands (e.g., local vs global, semantic vs photometric). In particular, prevalent ControlNet and OmniControl variants combine multiple conditioning signals (e.g., text, mask, reference) via static concatenation or additive adapters which cannot dynamically prioritize or suppress conflicting modalities, thus resulting in artifacts like color bleeding across mask boundaries, identity or style drift, and unpredictable behavior under multi-condition inputs. To address this, we propose Condition-Aware Routing of Experts (CARE-Edit) that aligns model computation with specific editing competencies. At its core, a lightweight latent-attention router assigns encoded diffusion tokens to four specialized experts--Text, Mask, Reference, and Base--based on multi-modal conditions and diffusion timesteps: (i) a Mask Repaint module first refines coarse user-defined masks for precise spatial guidance; (ii) the router applies sparse top-K selection to dynamically allocate computation to the most relevant experts; (iii) a Latent Mixture module subsequently fuses expert outputs, coherently integrating semantic, spatial, and stylistic information to the base images. Experiments validate CARE-Edit's strong performance on contextual editing tasks, including erasure, replacement, text-driven edits, and style transfer. Empirical analysis further reveals task-specific behavior of specialized experts, showcasing the importance of dynamic, condition-aware processing to mitigate multi-condition conflicts.

Related papers

• MDN-Control: Mask-Depth-Noise Guided Region Control for Multi-Subject Video Editing [19.25272895567409]
  Multi subject video editing modifies designated subjects while preserving non target content.<n>Existing approaches rely on masks and struggle to distinguish overlapping subjects or ensure consistent generation.<n>We propose MDN-Control, a training free framework jointly controlling target localization, occlusion geometry, and appearance.<n> Experiments on MSVBench show that MDN-Control achieves the lowest CM-Err and the highest Q-Edit, while maintaining competitive text alignment and temporal consistency.
  arXiv  Detail & Related papers  (2026-09-15T00:58:55Z)
• CoT-Edit: Let CoT Guide Instruction Video Editing [13.600094788792633]
  We propose a plan--guide--edit framework that bridges semantic intent and spatial execution.<n>In our framework, a Chain-of-Thought (CoT)-enhanced multimodal large language model (MLLM) serves as a planner.<n>These spatial priors then guide a box-conditioned mask generator, transforming ambiguous global retrieval into localized, context-aware refinement.
  arXiv  Detail & Related papers  (2026-08-02T09:20:15Z)
• AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization [55.06425570300248]
  We present AnyMS, a training-free framework for layout-guided multi-subject customization.<n>AnyMS leverages three input conditions: text prompt, subject images, and layout constraints.<n>AnyMS achieves state-of-the-art performance, supporting complex compositions and scaling to a larger number of subjects.
  arXiv  Detail & Related papers  (2025-12-29T15:26:25Z)
• Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance [17.81116161163605]
  Amodal completion, generating invisible parts of occluded objects, is vital for applications like image editing and AR.<n>We propose a Collaborative Multi-Agent Reasoning Framework based on upfront collaborative reasoning to overcome these issues.
  arXiv  Detail & Related papers  (2025-09-22T13:20:06Z)
• 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)
• MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models [10.798205956644317]
  We propose a training-free, inference-stage optimization approach that enables precise localized image manipulation in complex multi-object scenes, named MDE-Edit.<n>Extensive experiments demonstrate that MDE-Edit outperforms state-of-the-art methods in editing accuracy and visual quality, offering a robust solution for complex multi-object image manipulation tasks.
  arXiv  Detail & Related papers  (2025-05-08T10:01:14Z)
• Marmot: Object-Level Self-Correction via Multi-Agent Reasoning [55.74860093731475]
  Marmot is a novel and generalizable framework that leverages Multi-Agent Reasoning for Multi-Object Self-Correcting.<n>Marmot significantly improves accuracy in object counting, attribute assignment, and spatial relationships for image generation tasks.
  arXiv  Detail & Related papers  (2025-04-10T16:54:28Z)
• Disentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing [26.02149948089938]
  Instruction Influence Disentanglement (IID) is a novel framework enabling parallel execution of multiple instructions in a single denoising process.<n>We analyze self-attention mechanisms in DiTs and derive instruction-specific attention masks to disentangle each instruction's influence.<n>IID reduces diffusion steps while improving fidelity and instruction completion compared to existing baselines.
  arXiv  Detail & Related papers  (2025-04-07T07:26:25Z)
• Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation [70.95380821618711]
  Dichotomous Image (DIS) tasks require highly precise annotations.<n>Current generative models and techniques struggle with the issues of scene deviations, noise-induced errors, and limited training sample variability.<n>We introduce a novel approach, which provides a scalable solution for generating diverse and precise datasets.
  arXiv  Detail & Related papers  (2024-12-26T06:37:25Z)
• Addressing Text Embedding Leakage in Diffusion-based Image Editing [33.1686050396517]
  We introduce Attribute-Leakage-free Editing (ALE), a framework that tackles attribute leakage at its source.<n>ALE combines Object-Restricted Embeddings (ORE) to disentangle text embeddings, Region-Guided Blending for Cross-Attention Masking (RGB-CAM) for spatially precise attention, and Background Blending (BB) to preserve non-edited content.
  arXiv  Detail & Related papers  (2024-12-06T02:10:07Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• DiffEdit: Diffusion-based semantic image editing with mask guidance [64.555930158319]
  DiffEdit is a method to take advantage of text-conditioned diffusion models for the task of semantic image editing. Our main contribution is able to automatically generate a mask highlighting regions of the input image that need to be edited.
  arXiv  Detail & Related papers  (2022-10-20T17:16:37Z)

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.