Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein Loss
This work addresses a specific challenge in texture synthesis for computer vision applications, but it is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of capturing long-range constraints in neural texture synthesis without requiring user-added spatial tags or difficult-to-tune regularization terms, and proposed a method using Sliced Wasserstein Loss that achieved competitive results compared to other optimization-based algorithms.
In the past decade, exemplar-based texture synthesis algorithms have seen strong gains in performance by matching statistics of deep convolutional neural networks. However, these algorithms require regularization terms or user-added spatial tags to capture long range constraints in images. Having access to a user-added spatial tag for all situations is not always feasible, and regularization terms can be difficult to tune. Thus, we propose a new set of statistics for texture synthesis based on Sliced Wasserstein Loss, create a multi-scale method to synthesize textures without a user-added spatial tag, study the ability of our proposed method to capture long range constraints, and compare our results to other optimization-based, single texture synthesis algorithms.