Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

• URL: http://arxiv.org/abs/2606.15188v1
• Date: Sat, 13 Jun 2026 08:30:33 GMT
• Title: Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing
• Abstract summary: An unsuitable initial noise may lead to unsatisfactory editing results.<n>Recent inference-time scaling methods address this issue by sampling multiple initial noises and selecting better candidates.<n>We propose VeriLatent, a plug-and-play adaptive inference-time scaling framework with early-step latent verification for image editing.
• Score: 49.40982704974727
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruction-based image editing has made notable progress with recent advances in generative models. However, the quality of the edited result is still influenced by the randomly sampled initial noise, particularly in complex editing scenarios. An unsuitable initial noise may lead to unsatisfactory editing results. Recent inference-time scaling methods address this issue by sampling multiple initial noises and selecting better candidates. Nevertheless, most of them follow a decode-then-verify scheme which introduces an efficiency-accuracy trade-off. When decoding is performed after limited inference steps, the decoded images often remain too noisy for reliable assessment, whereas sufficiently denoised images require much higher computational cost. To address this issue, we propose VeriLatent, a plug-and-play adaptive inference-time scaling framework with early-step latent verification for image editing. Specifically, we propose a novel verifier that scores each initial noise through a latent-space editing activation map at an early stage. It identifies promising candidates by assessing whether they can induce an effective edit in the correct region. This enables efficient early pruning without decoding latents into images. Building on this, we further develop an adaptive search strategy for inference-time scaling. It allocates inference budgets according to editing difficulty, thereby reducing the number of function evaluations (NFE). Extensive experiments on multiple benchmarks and different base models demonstrate that VeriLatent consistently improves both editing performance and inference-time scaling efficiency.

Related papers

• From Scale to Speed: Adaptive Test-Time Scaling for Image Editing [42.704748740631885]
  Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time.<n>We propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance.
  arXiv  Detail & Related papers  (2026-02-24T09:13:16Z)
• TTSnap: Test-Time Scaling of Diffusion Models via Noise-Aware Pruning [53.52543819839442]
  A prominent approach to test-time scaling for text-to-image diffusion models formulates the problem as a search over multiple noise seeds.<n>We propose test-time scaling with noise-aware pruning (TTSnap), a framework that prunes low-quality candidates without fully denoising them.
  arXiv  Detail & Related papers  (2025-11-27T09:14:26Z)
• EditInfinity: Image Editing with Binary-Quantized Generative Models [64.05135380710749]
  We investigate the parameter-efficient adaptation of binary-quantized generative models for image editing.<n>Specifically, we propose EditInfinity, which adapts emphInfinity, a binary-quantized generative model, for image editing.<n>We propose an efficient yet effective image inversion mechanism that integrates text prompting rectification and image style preservation.
  arXiv  Detail & Related papers  (2025-10-23T05:06:24Z)
• Exploring Iterative Manifold Constraint for Zero-shot Image Editing [38.7483790652481]
  We propose a novel zero-shot editing paradigm dubbed ZZEdit.<n>It locates a qualified intermediate-inverted latent marked as $z_p$ as a better editing pivot.<n>Our ZZEdit performs iterative manifold constraint between the manifold of $M_p$ and $M_p-1$, leading to fewer fidelity errors.
  arXiv  Detail & Related papers  (2025-01-07T09:00:36Z)
• Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing [42.45138713525929]
  Effective editing requires inverting the source image into a latent space, a process often hindered by prediction errors inherent in DDIM inversion. We introduce the Logistic Schedule, a novel noise schedule designed to eliminate singularities, improve inversion stability, and provide a better noise space for image editing. Our approach requires no additional retraining and is compatible with various existing editing methods.
  arXiv  Detail & Related papers  (2024-10-24T14:07:02Z)
• PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing [63.38854614997581]
  We introduce PostEdit, a method that incorporates a posterior scheme to govern the diffusion sampling process.<n>The proposed PostEdit achieves state-of-the-art editing performance while accurately preserving unedited regions.<n>The method is both inversion- and training-free, necessitating approximately 1.5 seconds and 18 GB of GPU memory to generate high-quality results.
  arXiv  Detail & Related papers  (2024-10-07T09:04:50Z)
• Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models [54.641726517633025]
  We propose a new framework that uses pre-trained object counting techniques and object detectors to guide generation.<n>First, we optimize a counting token using an outer-loop loss computed on fully generated images.<n>Second, we introduce a detection-driven scaling term that corrects errors caused by viewpoint and proportion shifts.
  arXiv  Detail & Related papers  (2024-08-21T15:51:46Z)
• InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization [27.508861002013358]
  InitNO is a paradigm that refines the initial noise in semantically-faithful images. A strategically crafted noise optimization pipeline is developed to guide the initial noise towards valid regions. Our method, validated through rigorous experimentation, shows a commendable proficiency in generating images in strict accordance with text prompts.
  arXiv  Detail & Related papers  (2024-04-06T14:56:59Z)
• Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising [14.486289176696438]
  We propose a score priors-guided deep variational inference, namely ScoreDVI, for practical real-world denoising. We exploit a Non-$i.i.d$ Gaussian mixture model and variational noise posterior to model the real-world noise. Our method outperforms other single image-based real-world denoising methods and achieves comparable performance to dataset-based unsupervised methods.
  arXiv  Detail & Related papers  (2023-08-09T03:26:58Z)
• DETA: Denoised Task Adaptation for Few-Shot Learning [135.96805271128645]
  Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge. With only a handful of samples available, the adverse effect of either the image noise (a.k.a. X-noise) or the label noise (a.k.a. Y-noise) from support samples can be severely amplified. We propose DEnoised Task Adaptation (DETA), a first, unified image- and label-denoising framework to existing task adaptation approaches.
  arXiv  Detail & Related papers  (2023-03-11T05:23:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.