Lmser-pix2seq: Learning Stable Sketch Representations For Sketch Healing

Tengjie Li, Sicong Zang, Shikui Tu, Lei Xu

Keywords: sketch healing, Lmser, stable representations, bi-directional connections

Abstract: Sketch healing aims to recreate a complete sketch from the corrupted one. The sparse and abstract nature of the sketch makes it challenging due to the difficulty in learning. The features extracted from the corrupted sketch may be inconsistent with the ones from the corresponding full sketch. In this paper, we present Lmser-pix2seq to learn stable sketch representations against the missing information by employing a Least mean square error reconstruction (Lmser) block, which falls into encoder-decoder paradigm. Taking as input a corrupted sketch, the Lmser encoder computes the embeddings of structural patterns of the input, while the decoder reconstructs the complete sketch from the embeddings. We build bi-directional skip connections between the encoder and the decoder in our Lmser block. The feedback connections enable recurrent paths to receive more information about the reconstructed sketch produced by the decoder, which helps the encoder extract stable sketch features. The features captured by the Lmser block are eventually fed into a recurrent neural network decoder to recreate the sketches. Experimental results show that our Lmser-pix2seq outperforms the state-of-the-art methods in sketch healing, especially when the sketches are heavily masked or corrupted.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning