This paper proposes a novel location-aware deep-learning-based single image reflection removal method. Our network has a reflection detection module to regress a probabilistic reflection confidence map, taking multi-scale Laplacian features as inputs. This probabilistic map tells if a region is reflection-dominated or transmission-dominated, and it is used as a cue for the network to control the feature flow when predicting the reflection and transmission layers. We design our network as a recurrent network to progressively refine reflection removal results at each iteration. The novelty is that we leverage Laplacian kernel parameters to emphasize the boundaries of strong reflections. It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results. Extensive experiments verify the superior performance of the proposed method over state-of-the-art approaches. Our code and the pre-trained model can be found at https://github.com/zdlarr/Location-aware-SIRR.
翻译:本文提出一种新的定位感深学习的单一图像反射去除方法。 我们的网络有一个反射检测模块, 以回溯概率反射信心图, 以多比例的 Laplacian 特征作为投入。 这个概率映射图显示一个区域是否以反射为主或以传输为主, 并用作网络在预测反射和传输层时控制特征流的提示。 我们设计的网络是一个经常性网络, 以逐步完善每次迭代的反射结果。 新的是, 我们利用 Laplacian 内核参数来强调强烈反射的界限。 这有利于强烈反射探测, 并大大改善反射结果的质量。 广泛的实验可以核实拟议方法优于最新方法的优异性表现。 我们的代码和预先培训的模式可以在 https://github.com/zdlarr/Location-aware- SIRRR 上找到。