From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
Xiangyan Qu, Zhenlong Yuan, Jing Tang, Rui Chen, Datao Tang, Meng Yu, Lei Sun, Yancheng Bai, Xiangxiang Chu, Gaopeng Gou, Gang Xiong, Yujun Cai

TL;DR
This paper introduces ADE-CoT, an adaptive test-time scaling framework for image editing that improves efficiency and performance by dynamically allocating resources, early verification, and opportunistic stopping, outperforming existing methods.
Contribution
It proposes a novel adaptive scaling method for image editing that addresses resource inefficiency and unreliability in current test-time scaling approaches.
Findings
Achieves over 2x speedup compared to Best-of-N with similar sampling budgets.
Outperforms state-of-the-art editing models on multiple benchmarks.
Enhances editing efficiency and accuracy through adaptive strategies.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Multimodal Machine Learning Applications · Cell Image Analysis Techniques
