[논문] PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
·
Paper Review
https://shunsukesaito.github.io/PIFuHD/https://www.youtube.com/watch?v=uEDqCxvF5ycAbstractimage-based 3D human shape estimation은 Deep Neural Network의 등장으로 급격히 발전했다. 하지만, real world setting에서는 input image의 detail을 살리는데 어려움을 겪는데, 이 논문의 저자들은 이러한 어려움의 원인을 2가지 conflicting requirements에서 찾았다.Accurate predictions require large context, but precise predictions require high resolutionDue to memory limita..
[논문] PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
·
Paper Review
https://shunsukesaito.github.io/PIFu/AbstractWhat if PIFu?An implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object→ End-to-End deep learning method for digitizing highly detailed clothed humans that can infer both 3D surface and texture매우 복잡한 shape [hairstyles, clothing …] 뿐만 아니라 이것들의 변화나 변형도 unified way로 digitize할 수 있다PIFu는 사람의 ..