CVDec 5, 2018

An Unpaired Shape Transforming Method for Image Translation and Cross-Domain Retrieval

arXiv:1812.02134v31 citations
Originality Incremental advance
AI Analysis

This addresses the problem of shape transformation in images for applications like fashion and retrieval, though it appears incremental as it builds on existing unpaired translation methods.

The paper tackles unpaired geometric image-to-image translation by transferring object geometry across domains while preserving appearance, using a single model without paired training data. Results on datasets like VITON and CMU-Multi-PIE demonstrate effectiveness, with learned features also aiding item retrieval.

We address the problem of unpaired geometric image-to-image translation. Rather than transferring the style of an image as a whole, our goal is to translate the geometry of an object as depicted in different domains while preserving its appearance characteristics. Our model is trained in an unpaired fashion, i.e. without the need of paired images during training. It performs all steps of the shape transfer within a single model and without additional post-processing stages. Extensive experiments on the VITON, CMU-Multi-PIE and our own FashionStyle datasets show the effectiveness of the method. In addition, we show that despite their low-dimensionality, the features learned by our model are useful to the item retrieval task.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes