Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing

• URL: http://arxiv.org/abs/2510.08157v1
• Date: Thu, 09 Oct 2025 12:36:51 GMT
• Title: Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing
• Authors: Zhentao Zou, Zhengrong Yue, Kunpeng Du, Binlei Bao, Hanting Li, Haizhen Xie, Guozheng Xu, Yue Zhou, Yali Wang, Jie Hu, Xue Jiang, Xinghao Chen,
• Abstract summary: Chain-of-Thought (CoT) is limited in its ability to represent intricate visual layouts.<n>We propose Multimodal Reasoning Edit (MURE) to shift the visual editing process from purely text-based reasoning to a series of interleaved rationales.<n>We release the first CoT-Edit-14K dataset, comprising 14K high-quality editing examples.
• Score: 32.36623938012829
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image editing with natural language has gained significant popularity, yet existing methods struggle with intricate object intersections and fine-grained spatial relationships due to the lack of an explicit reasoning process. While Chain-of-Thought (CoT) has been explored to enhance reasoning, purely textual CoT or CoT augmented with coordinate information is fundamentally limited in its ability to represent intricate visual layouts and lacks the necessary visual cues to guide the generation of fine-grained, pixel-level details. To address these challenges, we propose Multimodal Reasoning Edit (MURE), a novel framework that shifts the visual editing process from purely text-based reasoning to a series of interleaved textual and visual rationales. Our framework performs image editing using a natively multimodal, interleaved text-image CoT. This approach generates a step-by-step chain of reasoning where a textual description is followed by a corresponding visual cue, such as a positional mask that defined intended edited regions or a representation of new content. Furthermore, to mitigate the hallucination phenomenon of large language models, we introduce Multimodal Deep Confidence (MMDC) reasoning paradigm. This paradigm explores a tree of visual reasoning paths at each step. By pruning low-quality branches using a deep confidence score from a reward model, it ensures the model consistently follows a high-quality trajectory towards the final edited result. The proposed method decomposes complex editing tasks into interdependent sub-tasks, achieving greater precision at each stage and yielding high-fidelity edited results. We define the formulation for interleaved text-image chains and release the first CoT-Edit-14K dataset, comprising 14K high-quality editing examples. Extensive experiments show that our method yields significant improvements across three image editing benchmarks.

Related papers

• ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning [76.2503352325492]
  ControlThinker is a novel framework that employs a "comprehend-then-generate" paradigm.<n>Latent semantics from control images are mined to enrich text prompts.<n>This enriched semantic understanding then seamlessly aids in image generation without the need for additional complex modifications.
  arXiv  Detail & Related papers  (2025-06-04T05:56:19Z)
• 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)
• GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing [66.33454784945293]
  Generation Chain-of-Thought (GoT) is a novel paradigm that enables generation and editing through an explicit language reasoning process.<n>GoT transforms conventional text-to-image generation and editing into a reasoning-guided framework.
  arXiv  Detail & Related papers  (2025-03-13T17:59:59Z)
• Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing [28.904419606450876]
  We present a Vision-guided and Mask-enhanced Adaptive Editing (ViMAEdit) method with three key novel designs. First, we propose to leverage image embeddings as explicit guidance to enhance the conventional textual prompt-based denoising process. Second, we devise a self-attention-guided iterative editing area grounding strategy.
  arXiv  Detail & Related papers  (2024-10-14T13:41:37Z)
• Text Guided Image Editing with Automatic Concept Locating and Forgetting [27.70615803908037]
  We propose a novel method called Locate and Forget (LaF) to locate potential target concepts in the image for modification. Compared to the baselines, our method demonstrates its superiority in text-guided image editing tasks both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2024-05-30T05:36:32Z)
• Contextualized Diffusion Models for Text-Guided Image and Video Generation [67.69171154637172]
  Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. We propose a novel and general contextualized diffusion model (ContextDiff) by incorporating the cross-modal context encompassing interactions and alignments between text condition and visual sample. We generalize our model to both DDPMs and DDIMs with theoretical derivations, and demonstrate the effectiveness of our model in evaluations with two challenging tasks: text-to-image generation, and text-to-video editing.
  arXiv  Detail & Related papers  (2024-02-26T15:01:16Z)
• Instilling Multi-round Thinking to Text-guided Image Generation [72.2032630115201]
  Single-round generation often overlooks crucial details, particularly in the realm of fine-grained changes like shoes or sleeves. We introduce a new self-supervised regularization, ie, multi-round regularization, which is compatible with existing methods. It builds upon the observation that the modification order generally should not affect the final result.
  arXiv  Detail & Related papers  (2024-01-16T16:19:58Z)
• Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment [10.82748329166797]
  We propose a framework that integrates a fusion of generated visual references and text guidance into the semantic latent space of a textitfrozen pre-trained diffusion model.<n>Using only a tiny neural network, our framework provides control over diverse content and attributes, driven intuitively by the text prompt.
  arXiv  Detail & Related papers  (2023-08-30T08:40:15Z)
• Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval [12.057465578064345]
  The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions.<n>We propose a novel TIPR framework to build fine-grained interactions and alignment between person images and the corresponding texts.
  arXiv  Detail & Related papers  (2023-07-18T08:23:46Z)
• Direct Inversion: Optimization-Free Text-Driven Real Image Editing with Diffusion Models [0.0]
  We propose an optimization-free and zero fine-tuning framework that applies complex and non-rigid edits to a single real image via a text prompt. We prove our method's efficacy in producing high-quality, diverse, semantically coherent, and faithful real image edits.
  arXiv  Detail & Related papers  (2022-11-15T01:07:38Z)
• Prompt-to-Prompt Image Editing with Cross Attention Control [41.26939787978142]
  We present an intuitive prompt-to-prompt editing framework, where the edits are controlled by text only. We show our results over diverse images and prompts, demonstrating high-quality synthesis and fidelity to the edited prompts.
  arXiv  Detail & Related papers  (2022-08-02T17:55:41Z)
• Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors [58.71128866226768]
  Recent text-to-image generation methods have incrementally improved the generated image fidelity and text relevancy. We propose a novel text-to-image method that addresses these gaps by (i) enabling a simple control mechanism complementary to text in the form of a scene. Our model achieves state-of-the-art FID and human evaluation results, unlocking the ability to generate high fidelity images in a resolution of 512x512 pixels.
  arXiv  Detail & Related papers  (2022-03-24T15:44:50Z)

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.