| | --- |
| | license: mit |
| | --- |
| | |
| |
|
| | # PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization |
| |
|
| | <a href="https://github.com/shunsukesaito/PIFu" target="_blank">https://github.com/shunsukesaito/PIFu</a> |
| |
|
| | This a checkpoint from the original project here are some important <a href="https://github.com/shunsukesaito/PIFu#demo" target="_blank">notes</a>: |
| |
|
| | > Warning: The released model is trained with mostly upright standing scans with weak perspectie projection and the pitch angle of 0 degree. Reconstruction quality may degrade for images highly deviated from trainining data. |
| |
|
| |
|
| | ``` |
| | @InProceedings{saito2019pifu, |
| | author = {Saito, Shunsuke and Huang, Zeng and Natsume, Ryota and Morishima, Shigeo and Kanazawa, Angjoo and Li, Hao}, |
| | title = {PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization}, |
| | booktitle = {The IEEE International Conference on Computer Vision (ICCV)}, |
| | month = {October}, |
| | year = {2019} |
| | } |
| | ``` |
| |
|
| |
|
| |
|
