pith. sign in

arxiv: 2504.13143 · v1 · pith:3IONYCKKnew · submitted 2025-04-17 · 💻 cs.CV · cs.AI

texttt{Complex-Edit}: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark

classification 💻 cs.CV cs.AI
keywords editingmodelsbenchmarkcomplexityinstructionsinstructionperformancesynthetic
0
0 comments X
read the original abstract

We introduce $\texttt{Complex-Edit}$, a comprehensive benchmark designed to systematically evaluate instruction-based image editing models across instructions of varying complexity. To develop this benchmark, we harness GPT-4o to automatically collect a diverse set of editing instructions at scale. Our approach follows a well-structured ``Chain-of-Edit'' pipeline: we first generate individual atomic editing tasks independently and then integrate them to form cohesive, complex instructions. Additionally, we introduce a suite of metrics to assess various aspects of editing performance, along with a VLM-based auto-evaluation pipeline that supports large-scale assessments. Our benchmark yields several notable insights: 1) Open-source models significantly underperform relative to proprietary, closed-source models, with the performance gap widening as instruction complexity increases; 2) Increased instructional complexity primarily impairs the models' ability to retain key elements from the input images and to preserve the overall aesthetic quality; 3) Decomposing a complex instruction into a sequence of atomic steps, executed in a step-by-step manner, substantially degrades performance across multiple metrics; 4) A straightforward Best-of-N selection strategy improves results for both direct editing and the step-by-step sequential approach; and 5) We observe a ``curse of synthetic data'': when synthetic data is involved in model training, the edited images from such models tend to appear increasingly synthetic as the complexity of the editing instructions rises -- a phenomenon that intriguingly also manifests in the latest GPT-4o outputs.

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 10 Pith papers

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

  1. SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing

    eess.AS 2026-06 unverdicted novelty 7.0

    SpeechEditBench provides seven atomic editing tasks, compositional multi-operation instructions, and an anchor-based protocol yielding target success, preservation success, and joint success metrics; evaluations show ...

  2. Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis

    cs.CV 2026-05 unverdicted novelty 7.0

    Presents Entity-Rubrics and AbstractEdit benchmark to measure image editing models on abstract intent, finding standard models struggle to balance edit intent with image preservation.

  3. Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off

    cs.CV 2026-03 unverdicted novelty 7.0

    Dress-ED is the first large-scale benchmark unifying virtual try-on, try-off, and text-guided garment editing with 146k verified samples plus a multimodal diffusion baseline.

  4. A Unified and Controllable Framework for Layered Image Generation with Visual Effects

    cs.CV 2026-01 unverdicted novelty 7.0

    LASAGNA produces layered images with integrated visual effects in a single pass, enabling drift-free edits via alpha compositing while releasing a 48K dataset and a 242-sample benchmark.

  5. InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation

    cs.CV 2025-12 unverdicted novelty 7.0

    InstructMoLE replaces per-token routing with instruction-guided global routing for mixture-of-low-rank-experts in diffusion transformers and adds an output-space orthogonality loss to improve multi-conditional image g...

  6. Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning

    cs.CV 2025-07 unverdicted novelty 7.0

    Presents Reason50K dataset and ReasonBrain framework for hypothetical instruction-based image editing that requires physical, temporal, causal, and story reasoning.

  7. 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.

  8. MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching

    cs.CV 2026-06 unverdicted novelty 5.0

    MT-EditFlow applies flow-matching RL with multi-reward aggregation to improve multi-turn image editing performance on models like FLUX.1-Kontext-dev by 6.85 points at turn-3.

  9. Towards Robust Sequential Decomposition for Complex Image Editing

    cs.CV 2026-05 unverdicted novelty 5.0

    Sequential decomposition trained on synthetic editing tasks improves robustness for complex image instructions and transfers to real images via co-training.

  10. Towards Robust Sequential Decomposition for Complex Image Editing

    cs.CV 2026-05 unverdicted novelty 4.0

    Develops a synthetic data pipeline for training sequential decomposition in generative image editing, showing robust gains with complexity and sim-to-real transfer via co-training.