PixText 以像素空間分組圖像生成高效精修場景文字
Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation
PixText 將局部場景文字精修建模為像素空間分組圖像生成,依據原圖只生成目標區域,並保留未編輯內容。在 Text Refinement Bench 上,PixText 的字形通過率為 83.06%,目標字元 OCR 完全匹配準確率為 94.66%,高於最強基線的 36.77% 和 52.31%。四步 MeanFlow 版本維持 81.84% 通過率,每張圖像的攤銷生成成本低於 1 GPU 秒。
Published on Oct 13
Authors:
,
,
,
,
,
Abstract
Generated images often have coherent layouts and visual content, yet local errors in small text and complex characters still limit their readability and practical use. Scene-text refinement requires accuracy, preservation, and efficiency. Existing methods based on variational autoencoders (VAEs) can lose fine strokes during reconstruction, while full-image editing can shift background colors. In this work, we introduce PixText, a model that formulates local text refinement as grouped image generation in pixel space. Conditioned on the original image, PixText generates only the target regions, preserves unedited content, and uses MeanFlow for four-step generation. We further introduce Text Refinement Bench to evaluate text correction and image preservation in generated images. On this benchmark, PixText achieves 83.06% glyph pass and 94.66% exact target-character OCR accuracy, versus 36.77% and 52.31% for the strongest baseline. Its four-step MeanFlow variant retains an 81.84% pass rate with less than one GPU-second of amortized generation cost per image.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.18284
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.18284 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.18284 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.18284 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co