FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing

• URL: http://arxiv.org/abs/2512.01755v1
• Date: Mon, 01 Dec 2025 15:00:47 GMT
• Title: FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing
• Abstract summary: We present FreqEdit, a training-free framework that enables stable editing across 10+ consecutive iterations.<n>Our approach comprises three synergistic components: (1) high-frequency feature injection from reference velocity fields to preserve fine-grained details, (2) an adaptive injection strategy that spatially modulates injection strength for precise region-specific control, and (3) a path compensation mechanism that periodically recalibrates the editing trajectory to prevent over-constraint.
• Score: 23.172235115031018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruction-based image editing through natural language has emerged as a powerful paradigm for intuitive visual manipulation. While recent models achieve impressive results on single edits, they suffer from severe quality degradation under multi-turn editing. Through systematic analysis, we identify progressive loss of high-frequency information as the primary cause of this quality degradation. We present FreqEdit, a training-free framework that enables stable editing across 10+ consecutive iterations. Our approach comprises three synergistic components: (1) high-frequency feature injection from reference velocity fields to preserve fine-grained details, (2) an adaptive injection strategy that spatially modulates injection strength for precise region-specific control, and (3) a path compensation mechanism that periodically recalibrates the editing trajectory to prevent over-constraint. Extensive experiments demonstrate that FreqEdit achieves superior performance in both identity preservation and instruction following compared to seven state-of-the-art baselines.

Related papers

• DuET: Dual Expert Trajectories for Diffusion Image Editing [42.49842620609682]
  We introduce DuET, a training-free inference method that temporarily relaxes source-image conditioning.<n>DuET consistently improves instruction relevance, semantic fidelity, and perceptual quality across diverse models and benchmarks.
  arXiv  Detail & Related papers  (2026-06-11T12:58:48Z)
• AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory [58.322260363577016]
  Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps.<n>We propose AnchorEdit, the first autoregressive (AR) diffusion-based framework designed specifically for high-resolution, long-term multi-turn editing.
  arXiv  Detail & Related papers  (2026-06-10T07:26:31Z)
• Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing [53.06890499054828]
  We propose an occlusion-aware selection framework that automatically identifies an optimal anchor frame for downstream editing.<n>Our framework enables precise and temporally consistent editing without requiring manual annotations.
  arXiv  Detail & Related papers  (2026-05-22T03:19:24Z)
• Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse [44.49646322759214]
  We show that a model's general abilities are closely associated with dominant singular directions of pretrained weight matrices.<n>We propose REVIVE, a plug-and-play framework that stabilizes sequential editing by explicitly preserving the dominant singular subspace.
  arXiv  Detail & Related papers  (2026-01-16T07:18:14Z)
• The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergy [71.39358554558667]
  We introduce SynPS, a method that Synergistically leverages Positional embeddings and Semantic information for faithful non-rigid image editing.<n>We propose an editing measurement that quantifies the required editing magnitude at each denoising step.<n>By adaptively integrating positional and semantic cues, SynPS effectively avoids both over- and under-editing.
  arXiv  Detail & Related papers  (2025-12-16T14:08:00Z)
• MonoVQD: Monocular 3D Object Detection with Variational Query Denoising and Self-Distillation [0.6144680854063939]
  We introduce MonoVQD, a novel framework designed to advance DETR-based monocular 3D detection.<n>Mask Separated Self-Attention mechanism enables the integration of the denoising process into a DETR architecture.<n>We present the Variational Query Denoising technique to address the vanishing problem of conventional denoising methods.<n> Rigorous experimentation demonstrates that MonoVQD achieves superior performance on the challenging KITTI monocular benchmark.
  arXiv  Detail & Related papers  (2025-06-14T14:49:12Z)
• Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model [60.82962950960996]
  We introduce UnifyEdit, a tuning-free method that performs diffusion latent optimization.<n>We develop two attention-based constraints: a self-attention (SA) preservation constraint for structural fidelity, and a cross-attention (CA) alignment constraint to enhance text alignment.<n>Our approach achieves a robust balance between structure preservation and text alignment across various editing tasks, outperforming other state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-08T01:02:50Z)
• PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing [63.38854614997581]
  We introduce PostEdit, a method that incorporates a posterior scheme to govern the diffusion sampling process.<n>The proposed PostEdit achieves state-of-the-art editing performance while accurately preserving unedited regions.<n>The method is both inversion- and training-free, necessitating approximately 1.5 seconds and 18 GB of GPU memory to generate high-quality results.
  arXiv  Detail & Related papers  (2024-10-07T09:04:50Z)
• TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models [53.757752110493215]
  We focus on a popular line of text-based editing frameworks - the edit-friendly'' DDPM-noise inversion approach. We analyze its application to fast sampling methods and categorize its failures into two classes: the appearance of visual artifacts, and insufficient editing strength. We propose a pseudo-guidance approach that efficiently increases the magnitude of edits without introducing new artifacts.
  arXiv  Detail & Related papers  (2024-08-01T17:27:28Z)
• Preserving Identity with Variational Score for General-purpose 3D Editing [48.314327790451856]
  Piva is a novel optimization-based method for editing images and 3D models based on diffusion models. We pinpoint the limitations in 2D and 3D editing, which causes detail loss and oversaturation. We propose an additional score distillation term that enforces identity preservation.
  arXiv  Detail & Related papers  (2024-06-13T09:32:40Z)
• Zero-Shot Video Editing through Adaptive Sliding Score Distillation [51.57440923362033]
  This study proposes a novel paradigm of video-based score distillation, facilitating direct manipulation of original video content. We propose an Adaptive Sliding Score Distillation strategy, which incorporates both global and local video guidance to reduce the impact of editing errors.
  arXiv  Detail & Related papers  (2024-06-07T12:33:59Z)
• FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models [44.26371926512843]
  We introduce a novel free approach that employs progressive $textbfFre$qu$textbfe$ncy truncation to refine the guidance of $textbfDiff$usion models for universal editing tasks. Our method achieves comparable results with state-of-the-art methods across a variety of editing tasks and on a diverse set of images.
  arXiv  Detail & Related papers  (2024-04-18T04:47:28Z)

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.