Author:
Wang Zongji,Liu Yunfei,Lu Feng
Abstract
AbstractIntrinsic image decomposition is an important and long-standing computer vision problem. Given an input image, recovering the physical scene properties is ill-posed. Several physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image decomposition. This work takes advantage of deep learning, and shows that it can solve this challenging computer vision problem with high efficiency. The focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input image. To achieve this goal, we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding space. We define feature distribution divergence to efficiently separate the feature vectors of different intrinsic components. The feature distributions are also constrained to fit the real ones through a feature distribution consistency. In addition, a data refinement approach is provided to remove data inconsistency from the Sintel dataset, making it more suitable for intrinsic image decomposition. Our method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent frames. Experimental results indicate that our proposed network structure can outperform the existing state-of-the-art.
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Computer Graphics and Computer-Aided Design,Computer Vision and Pattern Recognition
Reference60 articles.
1. Baslamisli, A. S.; Le, H. A.; Geyers, T. CNN based learning using reflection and retinex models for intrinsic image decomposition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6674–6683, 2018.
2. Land, E. H.; McCann, J. J. Lightness and retinex theory. Journal of the Optical Society of America Vol. 61, No. 1, 1–11, 1971.
3. Gehler, P. V.; Rother, C.; Kiefel, M.; Zhang, L. M.; Schölkopf, B. Recovering intrinsic images with a global sparsity prior on reflectance. In: Proceedings of the 24th International Conference on Neural Information Processing Systems, 765–773, 2011.
4. Shen, L.; Yeo, C. Intrinsic images decomposition using a local and global sparse representation of reflectance. In: Proceedings of the IEEE/CVF Computer Vision and Pattern Recognition Conference, 697–704, 2011.
5. Shen, L.; Tan, P.; Lin, S. Intrinsic image decomposition with non-local texture cues. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–7, 2008.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献