Open latethousandyear opened 6 days ago
Hi, thanks for your interset.
The camera pose plays an important role in Deformable-GS. Did you run on your own dataset or the scene mentioned in the README?
Hi, thanks for your interset.
The camera pose plays an important role in Deformable-GS. Did you run on your own dataset or the scene mentioned in the README?
the scene mentioned in the README
Maybe you used the HyperNeRF dataset? HyperNeRF is a dicey dataset with inaccurate camera pose. The problem with this dataset has been discussed in the paper. Since Deformable-GS can predict accurate and clean motion at a specific time. If the camera pose is not so accurate, it will fail to converge.
Hello! I did the experiment according to each step of the readme document, and the experimental environment was configured without problems, but the results I got were very bad, and the PSNR was only about 10, what is the reason?
![poor_result1](https://github.com/ingra14m/Deformable-3D-Gaussians/assets/171837606/39b92917-6986-4ee0-8e00-57b664913642)