Re-Identification Supervised Texture Generation
This addresses the texture generation problem in 3D human body modeling for applications like computer vision and graphics, but it is incremental as it builds on existing re-identification and rendering techniques.
The paper tackles the problem of generating high-quality human body textures from a single image by proposing an end-to-end learning strategy supervised by person re-identification, and it shows that the generated textures are of higher quality than other methods on pedestrian images.
The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years. However, the texture generation problem has not been fully discussed. In this paper, we propose an end-to-end learning strategy to generate textures of human bodies under the supervision of person re-identification. We render the synthetic images with textures extracted from the inputs and maximize the similarity between the rendered and input images by using the re-identification network as the perceptual metrics. Experiment results on pedestrian images show that our model can generate the texture from a single image and demonstrate that our textures are of higher quality than those generated by other available methods. Furthermore, we extend the application scope to other categories and explore the possible utilization of our generated textures.