arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.01540cs.CV
收藏

基于物理的图像本征分解阴影重建

Physics-based Shading Reconstruction for Intrinsic Image Decomposition

University of Amsterdam(阿姆斯特丹大学);DUniversum(3D宇宙公司)

Anil S. Baslamisli, Yang Liu, Sezer Karaoglu, Theo Gevers

摘要:

我们研究了使用光度不变性和深度学习来计算内在图像(阴影和阴影)。我们提出了基于物理模型的梯度描述符和阴影梯度描述符。使用描述符,隐藏过渡被掩蔽,并且以无学习无监督的方式直接从相应的RGB图像梯度计算初始稀疏阴影图。然后,提出了一种优化方法来重建全稠密阴影图。最后,我们将生成的着色图集成到一个新的深度学习框架中,以对其进行细化,并预测相应的灰度图像,以实现内在图像分解。通过这样做,我们是第一个直接解决纹理和强度模糊性问题的阴影估计。大规模实验表明,我们的方法由基于物理的不变描述子引导,在MIT固有图像,NIR-RGB固有图像,多光源固有图像,光谱固有图像,尽可能真实的情况下取得了优异的结果,并在Wild数据集中的固有图像上取得了有竞争力的结果,同时实现了最先进的阴影估计。

英文摘要:

We investigate the use of photometric invariance and deep learning to compute intrinsic images (albedo and shading). We propose albedo and shading gradient descriptors which are derived from physics-based models. Using the descriptors, albedo transitions are masked out and an initial sparse shading map is calculated directly from the corresponding RGB image gradients in a learning-free unsupervised manner. Then, an optimization method is proposed to reconstruct the full dense shading map. Finally, we integrate the generated shading map into a novel deep learning framework to refine it and also to predict corresponding albedo image to achieve intrinsic image decomposition. By doing so, we are the first to directly address the texture and intensity ambiguity problems of the shading estimations. Large scale experiments show that our approach steered by physics-based invariant descriptors achieve superior results on MIT Intrinsics, NIR-RGB Intrinsics, Multi-Illuminant Intrinsic Images, Spectral Intrinsic Images, As Realistic As Possible, and competitive results on Intrinsic Images in the Wild datasets while achieving state-of-the-art shading estimations.

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。

↑