arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.04009cs.CV
收藏

使用预测一致性和逐步细化估计相机响应函数,并扩展到深度学习

Estimation of Camera Response Function using Prediction Consistency and Gradual Refinement with an Extension to Deep Learning

National University of Singapore(新加坡国立大学)

Aashish Sharma, Robby T. Tan, Loong-Fah Cheong

摘要:

大多数现有的方法CRF估计从一个单一的图像无法处理一般的真实图像。例如,基于从边缘提取的色块的EdgeCRF仅在噪声不明显时有效,而对于许多真实图像而言并非如此;以及CRFNet,一种基于完全监督深度学习的最新方法仅适用于训练数据中的CRF,因此无法处理训练数据之外的其他可能的CRF。为了解决这些问题,我们引入了一种使用预测一致性和逐步细化的非深度学习方法。首先,我们更多地依赖于输入图像的补丁,这些补丁提供了更一致的预测。如果从补丁的预测更一致,这意味着补丁可能受噪声或任何劣质颜色组合的影响较小,因此,它可以更可靠的CRF估计。其次,我们采用了一个渐进的细化方案,其中我们从一个简单的CRF模型开始生成一个结果,这是更强大的噪声,但不太准确,然后我们逐渐增加模型的复杂性,以改善结果。这是因为一个简单的模型,虽然不太准确,过拟合噪声比复杂的模型。实验结果表明,该方法在白天和夜间的真实图像中的识别效果优于现有的单图像方法。我们进一步提出了一个更有效的深度学习扩展,它对测试输入图像执行测试时训练(基于无监督损失)。这为我们的方法提供了比CRFNet更好的泛化性能,使其更实际地适用于一般真实图像的CRF估计。

英文摘要:

Most existing methods for CRF estimation from a single image fail to handle general real images. For instance, EdgeCRF based on colour patches extracted from edges works effectively only when the presence of noise is insignificant, which is not the case for many real images; and, CRFNet, a recent method based on fully supervised deep learning works only for the CRFs that are in the training data, and hence fail to deal with other possible CRFs beyond the training data. To address these problems, we introduce a non-deep-learning method using prediction consistency and gradual refinement. First, we rely more on the patches of the input image that provide more consistent predictions. If the predictions from a patch are more consistent, it means that the patch is likely to be less affected by noise or any inferior colour combinations, and hence, it can be more reliable for CRF estimation. Second, we employ a gradual refinement scheme in which we start from a simple CRF model to generate a result which is more robust to noise but less accurate, and then we gradually increase the model's complexity to improve the result. This is because a simple model, while being less accurate, overfits less to noise than a complex model does. Our experiments show that our method outperforms the existing single-image methods for daytime and nighttime real images. We further propose a more efficient deep learning extension that performs test-time training (based on unsupervised losses) on the test input image. This provides our method better generalization performance than CRFNet making it more practically applicable for CRF estimation for general real images.

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。

↑