Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds

• URL: http://arxiv.org/abs/2608.03135v1
• Date: Tue, 04 Aug 2026 05:03:17 GMT
• Title: Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds
• Abstract summary: Text-to-image diffusion models often omit or merge concepts incorrectly with multiple concepts.<n>We propose Rectify-then-Diffuse (RTD), a training-free framework that rectifies the initial allocation once before standard denoising.<n>RTD achieves state-of-the-art compositional fidelity and robust gains.
• Score: 18.12683458124076
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Text-to-image diffusion models can generate individual concepts well, but they often omit or merge concepts incorrectly with multiple concepts. We trace these failures to an early coordination bottleneck: before denoising begins, prompt-conditioned attention may allocate different concepts to strongly overlapping spatial support, which can keep their attention coupled as denoising proceeds. This observation motivates treating compositional generation as a boundary-condition problem rather than repeatedly controlling the evolving trajectory. To this end, we propose Rectify-then-Diffuse (RTD), a training-free framework that rectifies the initial allocation once before standard denoising. Firstly, we propose Soft-Overlap Disentanglement (SOD), which converts normalized overlap between pilot concept maps into a differentiable and layout-agnostic separation objective. Secondly, we introduce Isotropic Gradient Rectification (IGR), which normalizes the SOD gradient and applies a bounded latent displacement with a consistent scale across prompts and initializations. Extensive experiments show that RTD achieves state-of-the-art compositional fidelity and robust gains. On the AE-Bench object pair subset, RTD improves BLIP-VQA by 45.8% and ImageReward by 19.6% over CO3 while running 2.3$\times$ faster. Code will be released at https://github.com/Z-yiwei/rectify-then-diffuse

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time [16.04233421396159]
  AnchorSteer is a training-free framework that exerts fine-grained control over.<n>textbfAnchorSteer and its components.<n>Experiments on GenEval and T2I-CompBench++ demonstrate that AnchorSteer consistently outperforms existing baselines in text--image alignment.
  arXiv  Detail & Related papers  (2026-07-29T09:08:57Z)
• Beyond Unfolding: 60x Faster One-Stage Unmixing for Closely-Spaced Infrared Small Targets [43.71958109614362]
  Closely-Spaced Infrared Small Targets (CSIST) typically exhibit energy overlap, manifesting as indistinguishable blobs in infrared images.<n>This ambiguity invalidates the one-to-one mapping assumption of traditional detection.<n>We propose a one-stage lightweight paradigm which demonstrates that deep unfolding is not necessary.
  arXiv  Detail & Related papers  (2026-07-17T14:42:51Z)
• StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion [41.23458880886283]
  Stipple patterns, point sets whose local density tracks a target image, are traditionally produced by per-density iteratives.<n>We present the first diffusion-based sampler that simultaneously satisfies a learned local point-distribution prior and a continuous, image-defined capacity constraint at inference.<n>A single trained checkpoint accepts arbitrary target densities at inference, generalizes to point budgets that were not seen during training, and produces stipples in time nearly independent of the output point count.
  arXiv  Detail & Related papers  (2026-05-15T10:12:42Z)
• Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction [45.25461515976432]
  Plug-and-Play diffusion prior (DP) frameworks have emerged as a powerful paradigm for imaging reconstruction.<n>We present a novel approach to resolving bias-hallucination trade-off, achieving state-of-the-art gradients with significantly accelerated convergence.
  arXiv  Detail & Related papers  (2026-02-26T16:58:43Z)
• Score Distillation of Flow Matching Models [67.86066177182046]
  We extend Score identity Distillation (SiD) to pretrained text-to-image flow-matching models.<n>SiD works out of the box across these models, in both data-free and data-aided settings.<n>This provides the first systematic evidence that score distillation applies broadly to text-to-image flow matching models.
  arXiv  Detail & Related papers  (2025-09-29T17:45:48Z)
• Continuous Speculative Decoding for Autoregressive Image Generation [27.308442169466975]
  Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation.<n> speculative decoding has effectively accelerated discrete autoregressive inference.<n>This work addresses challenges from low acceptance rate, inconsistent output distribution, and modified distribution without analytic expression.
  arXiv  Detail & Related papers  (2024-11-18T09:19:15Z)
• A Variational Perspective on Solving Inverse Problems with Diffusion Models [101.831766524264]
  Inverse tasks can be formulated as inferring a posterior distribution over data. This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. We propose a variational approach that by design seeks to approximate the true posterior distribution.
  arXiv  Detail & Related papers  (2023-05-07T23:00:47Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• Learning to Estimate Hidden Motions with Global Motion Aggregation [71.12650817490318]
  Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We introduce a global motion aggregation module to find long-range dependencies between pixels in the first image. We demonstrate that the optical flow estimates in the occluded regions can be significantly improved without damaging the performance in non-occluded regions.
  arXiv  Detail & Related papers  (2021-04-06T10:32:03Z)
• An Interpretation of Regularization by Denoising and its Application with the Back-Projected Fidelity Term [55.34375605313277]
  We show that the RED gradient can be seen as a (sub)gradient of a prior function--but taken at a denoised version of the point. We propose to combine RED with the Back-Projection (BP) fidelity term rather than the common Least Squares (LS) term that is used in previous works.
  arXiv  Detail & Related papers  (2021-01-27T18:45:35Z)
• A Contrastive Learning Approach for Training Variational Autoencoder Priors [137.62674958536712]
  Variational autoencoders (VAEs) are one of the powerful likelihood-based generative models with applications in many domains. One explanation for VAEs' poor generative quality is the prior hole problem: the prior distribution fails to match the aggregate approximate posterior. We propose an energy-based prior defined by the product of a base prior distribution and a reweighting factor, designed to bring the base closer to the aggregate posterior.
  arXiv  Detail & Related papers  (2020-10-06T17:59:02Z)

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.