The reviewed record of science sign in
Pith

arxiv: 2506.04158 · v1 · pith:6SUYVLX4 · submitted 2025-06-04 · cs.CV

Image Editing As Programs with Diffusion Models

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:6SUYVLX4record.jsonopen to challenge →

classification cs.CV
keywords editingieapimagediffusionmodelsacrosschangescomplex
0
0 comments X
read the original abstract

While diffusion models have achieved remarkable success in text-to-image generation, they encounter significant challenges with instruction-driven image editing. Our research highlights a key challenge: these models particularly struggle with structurally inconsistent edits that involve substantial layout changes. To mitigate this gap, we introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture. At its core, IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations. Each operation is implemented via a lightweight adapter sharing the same DiT backbone and is specialized for a specific type of edit. Programmed by a vision-language model (VLM)-based agent, these operations collaboratively support arbitrary and structurally inconsistent transformations. By modularizing and sequencing edits in this way, IEAP generalizes robustly across a wide range of editing tasks, from simple adjustments to substantial structural changes. Extensive experiments demonstrate that IEAP significantly outperforms state-of-the-art methods on standard benchmarks across various editing scenarios. In these evaluations, our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions. Codes are available at https://github.com/YujiaHu1109/IEAP.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Semantic Granularity Navigation in Image Editing

    cs.CV 2026-05 unverdicted novelty 6.0

    NaviEdit reallocates fixed step budgets in diffusion rollouts to intermediate scales for improved semantic editability while preserving fidelity via a self-consistency contract.

  2. Meta-CoT: Enhancing Granularity and Generalization in Image Editing

    cs.CV 2026-04 unverdicted novelty 6.0

    Meta-CoT uses two-level decomposition of editing operations into meta-tasks and a CoT consistency reward to improve granularity and generalization, reporting 15.8% gains across 21 tasks.

  3. InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space

    cs.CV 2026-06 unverdicted novelty 5.0

    InstantRetouch performs efficient high-fidelity language-guided retouching via bilateral grid prediction of affine transforms combined with variational score distillation from diffusion models.

  4. DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents

    cs.AI 2026-05 unverdicted novelty 5.0

    DataEvolver introduces a reusable framework with generation-time self-correction and validation-time self-expansion loops that improves visual datasets, shown to outperform baselines on an object-rotation task.

  5. Semantic Granularity Navigation in Image Editing

    cs.CV 2026-05 unverdicted novelty 4.0

    NaviEdit is a training-free inference-time controller that decouples edit progress from model scale traversal in diffusion-based image editing via self-consistency, reporting average gains across editors and backbones.