Pith. sign in

REVIEW 5 cited by

KV-Edit: Training-Free Image Editing for Precise Background Preservation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.17363 v3 pith:VJAKYF42 submitted 2025-02-24 cs.CV

Tianrui Zhu , Shiyi Zhang , Jiawei Shao , Yansong Tang This is my paper
classification cs.CV
keywords backgroundimagekv-editeditingapproachcacheconsistencycontent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns with the target. Here, we propose KV-Edit, a training-free approach that uses KV cache in DiTs to maintain background consistency, where background tokens are preserved rather than regenerated, eliminating the need for complex mechanisms or expensive training, ultimately generating new content that seamlessly integrates with the background within user-provided regions. We further explore the memory consumption of the KV cache during editing and optimize the space complexity to $O(1)$ using an inversion-free method. Our approach is compatible with any DiT-based generative model without additional training. Experiments demonstrate that KV-Edit significantly outperforms existing approaches in terms of both background and image quality, even surpassing training-based methods. Project webpage is available at https://xilluill.github.io/projectpages/KV-Edit

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing

    cs.CV 2025-06 conditional novelty 7.0 of 10

    Direct Noise Alignment iteratively moves a random Gaussian noise until the model's predicted velocity matches the straight-line velocity to the image, reducing inversion drift and giving the best reported fidelity-edi...

  2. EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal

    cs.CV 2025-12 conditional novelty 6.0 of 10

    EraseLoRA removes masked objects by having an MLLM separate target, non-target foreground, and background, then test-time LoRA optimization aggregates background subtypes to reconstruct the occluded region.

  3. The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A training-free diffusion framework creates condition-aware facial aging trees from one photo, balancing identity, age, and prompt-controlled attributes.

  4. Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent

    cs.CV 2025-08 conditional novelty 5.0 of 10

    DescriptiveEdit turns semantic editing into reference-conditioned text-to-image generation, reporting state-of-the-art scores on the Emu Edit benchmark with a frozen backbone and about 75M trainable parameters.

  5. DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing

    cs.CV 2025-06 conditional novelty 4.0 of 10

    DFVEdit edits videos by iteratively subtracting a conditional delta flow vector, the difference between the model's predictions under the target and source prompts, from the latent representation of the source video.

Pith tools