Recently, effort has been made to apply deep learning to the detection of mesh saliency. However, one major barrier is to collect a large amount of vertex-level annotation as saliency ground truth for training the neural networks. Quite a few pilot studies showed that this task is quite difﬁcult. In this work, we solve this problem by developing a novel network trained in a weakly supervised manner. The training is end-to-end and does not require any saliency ground truth but only the class membership of meshes. Our Classiﬁcation-for-Saliency CNN (CfS-CNN) employs a multi-view setup and contains a newly designed two-channel structure which integrates view-based features of both classiﬁcation and saliency. It essentially transfers knowledge from 3D object classiﬁcation to mesh saliency. Our approach signiﬁcantly outperforms the existing state-of-the-art methods according to extensive experimental results. Also, the CfS-CNN can be directly used for scene saliency. We showcase two novel applications based on scene saliency to demonstrate its utility.
|Journal||IEEE Transactions on Visualization and Computer Graphics|
|Early online date||18 Jul 2019|
|Publication status||E-pub ahead of print - 18 Jul 2019|
- Mesh saliency
- Deep learning
- Transfer learning
- weak supervision