IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-view Human Reconstruction
This work addresses the problem of accurate 3D human reconstruction from single images for applications in computer vision and graphics, representing an incremental improvement over prior methods like PIFuHD.
The paper tackles single-view human reconstruction by proposing IntegratedPIFu, a pixel-aligned implicit model that integrates depth and human parsing information, introduces depth-oriented sampling to reduce artifacts, and uses a new architecture with fewer parameters, resulting in significantly outperforming existing state-of-the-art methods.
We propose IntegratedPIFu, a new pixel aligned implicit model that builds on the foundation set by PIFuHD. IntegratedPIFu shows how depth and human parsing information can be predicted and capitalised upon in a pixel-aligned implicit model. In addition, IntegratedPIFu introduces depth oriented sampling, a novel training scheme that improve any pixel aligned implicit model ability to reconstruct important human features without noisy artefacts. Lastly, IntegratedPIFu presents a new architecture that, despite using less model parameters than PIFuHD, is able to improves the structural correctness of reconstructed meshes. Our results show that IntegratedPIFu significantly outperforms existing state of the arts methods on single view human reconstruction. Our code has been made available online.