Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation

• URL: http://arxiv.org/abs/2503.06506v1
• Date: Sun, 09 Mar 2025 08:18:43 GMT
• Title: Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation
• Authors: Amir Mohammad Izadi, Seyed Mohammad Hadi Hosseini, Soroush Vafaie Tabar, Ali Abdollahi, Armin Saghafian, Mahdieh Soleymani Baghshah,
• Abstract summary: We present an innovative, training-free method that incorporates tailored objectives to account for textual constraints.<n>Our method, relying solely on our proposed objective functions, significantly enhances compositionality, achieving a 24% improvement in human evaluation.<n>Our fine-grained noise refinement proves effective, boosting performance by up to 5%.
• Score: 2.1457109220047137
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts, such as entity missing, attribute binding errors, and incorrect relationships remains a formidable challenge. In response, we present an innovative, training-free method that directly addresses these challenges by incorporating tailored objectives to account for textual constraints. Unlike layout-based approaches that enforce rigid structures and limit diversity, our proposed approach offers a more flexible arrangement of the scene by imposing just the extracted constraints from the text, without any unnecessary additions. These constraints are formulated as losses-entity missing, entity mixing, attribute binding, and spatial relationships, integrated into a unified loss that is applied in the first generation stage. Furthermore, we introduce a feedback-driven system for fine-grained initial noise refinement. This system integrates a verifier that evaluates the generated image, identifies inconsistencies, and provides corrective feedback. Leveraging this feedback, our refinement method first targets the unmet constraints by refining the faulty attention maps caused by initial noise, through the optimization of selective losses associated with these constraints. Subsequently, our unified loss function is reapplied to proceed the second generation phase. Experimental results demonstrate that our method, relying solely on our proposed objective functions, significantly enhances compositionality, achieving a 24% improvement in human evaluation and a 25% gain in spatial relationships. Furthermore, our fine-grained noise refinement proves effective, boosting performance by up to 5%. Code is available at https://github.com/hadi-hosseini/noise-refinement.

Related papers

• Active Adversarial Noise Suppression for Image Forgery Localization [56.98050814363447]
  We introduce an Adversarial Noise Suppression Module (ANSM) that generate a defensive perturbation to suppress the attack effect of adversarial noise.<n>To our best knowledge, this is the first report of adversarial defense in image forgery localization tasks.
  arXiv  Detail & Related papers  (2025-06-15T14:53:27Z)
• Noise Consistency Regularization for Improved Subject-Driven Image Synthesis [55.75426086791612]
  Fine-tuning Stable Diffusion enables subject-driven image synthesis by adapting the model to generate images containing specific subjects.<n>Existing fine-tuning methods suffer from two key issues: underfitting, where the model fails to reliably capture subject identity, and overfitting, where it memorizes the subject image and reduces background diversity.<n>We propose two auxiliary consistency losses for diffusion fine-tuning. First, a prior consistency regularization loss ensures that the predicted diffusion noise for prior (non-subject) images remains consistent with that of the pretrained model, improving fidelity.
  arXiv  Detail & Related papers  (2025-06-06T19:17:37Z)
• Score-Based Turbo Message Passing for Plug-and-Play Compressive Image Recovery [24.60447255507278]
  Off-the-shelf image denoisers mostly rely on some generic or hand-crafted priors for denoising. We devise a message passing framework that integrates a score-based minimum mean squared error (MMSE) denoiser for compressive image recovery.
  arXiv  Detail & Related papers  (2025-03-28T04:30:58Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• E2ED^2:Direct Mapping from Noise to Data for Enhanced Diffusion Models [15.270657838960114]
  Diffusion models have established themselves as the de facto primary paradigm in visual generative modeling.<n>We present a novel end-to-end learning paradigm that establishes direct optimization from the final generated samples to initial noises.<n>Our method achieves substantial performance gains in terms of Fr'eche't Inception Distance (FID) and CLIP score, even with fewer sampling steps.
  arXiv  Detail & Related papers  (2024-12-30T16:06:31Z)
• 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. The proposed PostEdit achieves state-of-the-art editing performance while accurately preserving unedited regions. 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)
• Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration [64.84134880709625]
  We show that it is possible to perform domain adaptation via the noise space using diffusion models.<n>In particular, by leveraging the unique property of how auxiliary conditional inputs influence the multi-step denoising process, we derive a meaningful diffusion loss.<n>We present crucial strategies such as channel-shuffling layer and residual-swapping contrastive learning in the diffusion model.
  arXiv  Detail & Related papers  (2024-06-26T17:40:30Z)
• 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)
• ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks [43.42682181017004]
  In this paper, we replace the image input with text for Vision-language training. Inspired by prior noise injection methods, we introduce Adaptive ranged cosine Similarity injected noise (ArcSin) Our empirical results demonstrate that these models closely rival those trained on images in terms of performance.
  arXiv  Detail & Related papers  (2024-02-27T08:20:45Z)
• Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
  This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
  arXiv  Detail & Related papers  (2024-01-25T08:11:27Z)
• Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Models [58.46926334842161]
  This work illuminates the fundamental reasons for such misalignment, pinpointing issues related to low attention activation scores and mask overlaps. We propose two novel objectives, the Separate loss and the Enhance loss, that reduce object mask overlaps and maximize attention scores. Our method diverges from conventional test-time-adaptation techniques, focusing on finetuning critical parameters, which enhances scalability and generalizability.
  arXiv  Detail & Related papers  (2023-12-10T22:07:42Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution [5.258555266148511]
  Single image super-resolution (SISR) is an ill-posed problem with an indeterminate number of valid solutions. We show that the root cause of these pattern artifacts can be traced back to a mismatch between the pre-training objective of perceptual loss and the super-resolved objective.
  arXiv  Detail & Related papers  (2020-05-15T12:36:54Z)
• A recurrent cycle consistency loss for progressive face-to-face synthesis [5.71097144710995]
  This paper addresses a major flaw of the cycle consistency loss when used to preserve the input appearance in the face-to-face synthesis domain. We show that the images generated by a network trained using this loss conceal a noise that hinders their use for further tasks. We propose a ''recurrent cycle consistency loss'' which for different sequences of target attributes minimises the distance between the output images.
  arXiv  Detail & Related papers  (2020-04-14T16:53:41Z)

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.