From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

2026-02-24

AI Summary

This work addresses three key challenges in Chain-of-Thought (CoT) approaches for image editing—inefficient resource allocation, unreliable early-stage verification, and redundant outputs—by proposing ADE-CoT, a novel framework that introduces the first adaptive test-time scaling mechanism tailored for image editing. ADE-CoT enhances efficiency and performance through difficulty-aware dynamic budget allocation, edit-specific pruning based on spatial localization and description consistency, and an intent-alignment-driven opportunistic early termination strategy. Extensive experiments demonstrate that ADE-CoT achieves over 2× acceleration across three state-of-the-art editing models and benchmarks while surpassing the edit quality of Best-of-N under the same computational budget.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image and instruction. This mismatch causes three challenges when applying Image-CoT to editing: inefficient resource allocation with fixed sampling budgets, unreliable early-stage verification using general MLLM scores, and redundant edited results from large-scale sampling. To address this, we propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance. It incorporates three key strategies: (1) a difficulty-aware resource allocation that assigns dynamic budgets based on estimated edit difficulty; (2) edit-specific verification in early pruning that uses region localization and caption consistency to select promising candidates; and (3) depth-first opportunistic stopping, guided by an instance-specific verifier, that terminates when intent-aligned results are found. Extensive experiments on three SOTA editing models (Step1X-Edit, BAGEL, FLUX.1 Kontext) across three benchmarks show that ADE-CoT achieves superior performance-efficiency trade-offs. With comparable sampling budgets, ADE-CoT obtains better performance with more than 2x speedup over Best-of-N.

Problem

• Image Editing
• Test-Time Scaling
• Resource Allocation
• Early Verification
• Redundant Sampling

Innovation

• Adaptive Test-Time Scaling
• Image Editing
• Chain-of-Thought
• Efficiency-Performance Trade-off
• Instance-Specific Verification