TEMPEH
TEMPEH copied to clipboard
TimoBolkart
TEMPEH reconstructs 3D heads in dense semantic correspondence from calibrated multi-view images in about 0.3 seconds.
Hi, I would be interested on having the FLAME parameters for our dataset, however, when I downloaded the "FLAME Registrations" I can only find the final reconstructions. Would it be...
We have noticed variations in the orientation of different expressions among individuals in the downloaded data. This has caused challenges in processing and analyzing the data. We would like to...
Thank you for your impressive work! I want to apply our data, multiple images (same img size as your project ) and same format calibration data(*.tka) used in your project...
@TimoBolkart I am getting this error, when trying to run the coarse stage inference: loaded pretrained resume_checkpoint(): found 1 models Resuming progress from 600001 iteration from model path ./runs/coarse\coarse__TEMPEH_final\checkpoints\model_00600000.pth Traceback...
May i know how to run the code . I am not able to find how to run . can some one help me how to do it. Thanks.
Hello, I am really impressed by this work and want to test this work on our multi-view captured dataset. I wanted to know if there is a preprocessing pipeline available...
https://github.com/TimoBolkart/TEMPEH/blob/90cc1e5c2a3d5866efb22e7a05d36295869acae6/utils/camera.py#L79 Current code: `radial_distortion = np.array([K1, K2]).reshape(-1,)` Proposed replacement: `radial_distortion = np.array([K1, K2]).ravel()` Both reshape(-1,) and ravel() flatten arrays into 1-D. Performance: ravel() is consistently faster than reshape(-1,), as it...
Metadata
Owner
Metadata
TEMPEH reconstructs 3D heads in dense semantic correspondence from calibrated multi-view images in about 0.3 seconds.