FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL

• URL: http://arxiv.org/abs/2506.05501v1
• Date: Thu, 05 Jun 2025 18:36:33 GMT
• Title: FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL
• Authors: Kaihang Pan, Wendong Bu, Yuruo Wu, Yang Wu, Kai Shen, Yunfei Li, Hang Zhao, Juncheng Li, Siliang Tang, Yueting Zhuang,
• Abstract summary: We propose FocusDiff to enhance fine-grained text-image semantic alignment.<n>We construct a new dataset of paired texts and images with similar overall expressions but distinct local semantics.<n>Our approach achieves state-of-the-art performance on existing text-to-image benchmarks and significantly outperforms prior methods on PairComp.
• Score: 78.59912944698992
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but different fine-grained semantics -- reveals that existing models struggle with fine-grained text-image alignment thus failing to realize precise control over visual tokens. To address this, we propose FocusDiff, which enhances fine-grained text-image semantic alignment by focusing on subtle differences between similar text-image pairs. We construct a new dataset of paired texts and images with similar overall expressions but distinct local semantics, further introducing a novel reinforcement learning algorithm to emphasize such fine-grained semantic differences for desired image generation. Our approach achieves state-of-the-art performance on existing text-to-image benchmarks and significantly outperforms prior methods on PairComp.

Related papers

• VSC: Visual Search Compositional Text-to-Image Diffusion Model [15.682990658945682]
  We introduce a novel compositional generation method that leverages pairwise image embeddings to improve attribute-object binding.<n>Our approach decomposes complex prompts into sub-prompts, generates corresponding images, and computes visual prototypes that fuse with text embeddings to enhance representation.<n>Our approaches outperform existing compositional text-to-image diffusion models on the benchmark T2I CompBench, achieving better image quality, evaluated by humans, and emerging robustness under scaling number of binding pairs in the prompt.
  arXiv  Detail & Related papers  (2025-05-02T08:31:43Z)
• Aligning Text to Image in Diffusion Models is Easier Than You Think [47.623236425067326]
  SoftREPA is a lightweight contrastive fine-tuning strategy that leverages soft text tokens for representation alignment.<n>Our method explicitly increases the mutual information between text and image representations, leading to enhanced semantic consistency.
  arXiv  Detail & Related papers  (2025-03-11T10:14:22Z)
• Contextualized Diffusion Models for Text-Guided Image and Video Generation [67.69171154637172]
  Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. We propose a novel and general contextualized diffusion model (ContextDiff) by incorporating the cross-modal context encompassing interactions and alignments between text condition and visual sample. We generalize our model to both DDPMs and DDIMs with theoretical derivations, and demonstrate the effectiveness of our model in evaluations with two challenging tasks: text-to-image generation, and text-to-video editing.
  arXiv  Detail & Related papers  (2024-02-26T15:01:16Z)
• Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering [118.53208190209517]
  We propose a framework to learn the proper textual descriptions for diffusion models through prompt learning. Our method can effectively learn the prompts to improve the matches between the input text and the generated images.
  arXiv  Detail & Related papers  (2024-01-12T03:46:29Z)
• Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning [13.357749288588039]
  Previous works leverage the CLIP's cross-modal association ability for image captioning, relying solely on textual information under unsupervised settings. This paper proposes a novel method to address these issues by incorporating synthetic image-text pairs. A pre-trained text-to-image model is deployed to obtain images that correspond to textual data, and the pseudo features of generated images are optimized toward the real ones in the CLIP embedding space.
  arXiv  Detail & Related papers  (2023-12-14T12:39:29Z)
• RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment [112.45442468794658]
  We propose a two-stage coarse-to-fine semantic re-alignment method, named RealignDiff. In the coarse semantic re-alignment phase, a novel caption reward is proposed to evaluate the semantic discrepancy between the generated image caption and the given text prompt. The fine semantic re-alignment stage employs a local dense caption generation module and a re-weighting attention modulation module to refine the previously generated images from a local semantic view.
  arXiv  Detail & Related papers  (2023-05-31T06:59:21Z)
• Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models [52.29800567587504]
  We propose a learnable sampling model, Text-Conditioned Token Selection (TCTS), to select optimal tokens via localized supervision with text information. TCTS improves not only the image quality but also the semantic alignment of the generated images with the given texts. We validate the efficacy of TCTS combined with Frequency Adaptive Sampling (FAS) with various generative tasks, demonstrating that it significantly outperforms the baselines in image-text alignment and image quality.
  arXiv  Detail & Related papers  (2023-04-04T03:52:49Z)
• WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models [8.334487584550185]
  We present a latent diffusion-based method for styled text-to-text-content-image generation on word-level. Our proposed method is able to generate realistic word image samples from different writer styles. We show that the proposed model produces samples that are aesthetically pleasing, help boosting text recognition performance, and get similar writer retrieval score as real data.
  arXiv  Detail & Related papers  (2023-03-29T10:19:26Z)
• Variational Distribution Learning for Unsupervised Text-to-Image Generation [42.3246826401366]
  We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. We employ a pretrained CLIP model, which is capable of properly aligning embeddings of images and corresponding texts in a joint space. We optimize a text-to-image generation model by maximizing the data log-likelihood conditioned on pairs of image-text CLIP embeddings.
  arXiv  Detail & Related papers  (2023-03-28T16:18:56Z)

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.