3D Human Texture Estimation from a Single Image with Transformers
This addresses the problem of realistic 3D human modeling for computer vision applications, but it is incremental as it builds on existing texture estimation methods.
The paper tackles 3D human texture estimation from a single image by proposing a Transformer-based framework that overcomes CNN limitations, achieving state-of-the-art results in quantitative and qualitative experiments.
We propose a Transformer-based framework for 3D human texture estimation from a single image. The proposed Transformer is able to effectively exploit the global information of the input image, overcoming the limitations of existing methods that are solely based on convolutional neural networks. In addition, we also propose a mask-fusion strategy to combine the advantages of the RGB-based and texture-flow-based models. We further introduce a part-style loss to help reconstruct high-fidelity colors without introducing unpleasant artifacts. Extensive experiments demonstrate the effectiveness of the proposed method against state-of-the-art 3D human texture estimation approaches both quantitatively and qualitatively.