arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.04291eess.IVcs.CV
收藏

Diffusion in the Dark:一种用于弱光文本识别的扩散模型

Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition

Stanford University(斯坦福大学)

Cindy M. Nguyen, Eric R. Chan, Alexander W. Bergman, Gordon Wetzstein

摘要:

捕获图像是高级任务(如场景文本识别)自动化的关键部分。低光照条件对高级感知堆栈提出了挑战,这些堆栈通常在光照良好、无伪影的图像上进行优化。低光图像的重建方法可以产生光线充足的图像,但通常以牺牲对下游任务至关重要的高频细节为代价。我们提出了一种用于文本识别的低亮度图像重建的扩散模型--黑暗中的扩散(DiD)。DiD提供了与最先进的(SOTA)具有质量竞争力的重建,同时即使在非常嘈杂、黑暗的条件下也能保留高频细节。我们证明了DiD在没有任何特定任务优化的情况下,在真实图像的低光照文本识别中可以胜过SOTA低光照方法,从而增强了扩散模型解决不适定逆问题的潜力。

英文摘要:

Capturing images is a key part of automation for high-level tasks such as scene text recognition. Low-light conditions pose a challenge for high-level perception stacks, which are often optimized on well-lit, artifact-free images. Reconstruction methods for low-light images can produce well-lit counterparts, but typically at the cost of high-frequency details critical for downstream tasks. We propose Diffusion in the Dark (DiD), a diffusion model for low-light image reconstruction for text recognition. DiD provides qualitatively competitive reconstructions with that of state-of-the-art (SOTA), while preserving high-frequency details even in extremely noisy, dark conditions. We demonstrate that DiD, without any task-specific optimization, can outperform SOTA low-light methods in low-light text recognition on real images, bolstering the potential of diffusion models to solve ill-posed inverse problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑