Tensor4D
Tensor4D copied to clipboard
DSaurus
This is the official implementation of Tensor4D: Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering.
Hello, I noticed that after training, it's possible to obtain images and normals from your method. Could you please explain how to generate a mesh? I noticed that in the...
Hi thanks for the great work! How do you compute the scale_mat in preprocess.py? How can we change this for our own data? Thanks
Is it possible to run tensor4d on a random monocular video？ it seems like build a custom dataset is relying on "calibration_full.json", but I don't know how to get a...
Thanks for your wonderful work. I tried adapting Tensor4D to the D-NeRF dataset presented in the paper, such as "Standup" and "Jumpingjacks". This involves converting between the DTU coordinate system...
Amazing work; great job to everyone that did this - do you know if it's possible to change the pose/expression parameters of the reconstruction? for example changing hand movements; etc...
Hi! Thank you for your great work. Could tensor4d be extended to handle scenes without masks? The multi-view captures in these scenes may contain foreground moving objects/human and static backgrounds.
Hey there! I found that the Tensor4D uses the eikonal loss to get smoother results. I wonder about the actual performance of the eikonal loss since it is not reported...
I am getting noisy results, mainly at the edges of objects, as shown below. I am training a static scene and have tried both feature_type = "4d" and "3d". Do...
Excellent work! How much memory is needed to run this code (train and inference)?
