-
Hi, thank you again for the amazing work. I was wondering how to render the generated 4D representation back to a monocular video. I would like to have a video of the rendered scene from the same poi…
-
Hi thank you very much for your work. I am wondering, is it possible to render the training back to the resolution and size of the original video? I see that the rendering is done with a nerfstudio fu…
-
Hi, thanks for this fantastic work! When reconstructing the 3D face model from a video of a subject, it seems that the current demo code reconstructs the 3D face frame by frame, as in [ this code](htt…
-
Hello author, is it possible to take videos of local scenes and then reconstruct dense maps through this algorithm
-
Dear authors, thanks for your awesome work. Could you please provide a inference code for the video tokenizer reconstruction. I wrote one but found that the reconstruction results are bad after 4 fram…
-
Hi dear authors, thank you for your great work!
But I wonder why the resolutions of input video frames are reshaped into square ones (i.e. 512*512)? Is that an obligatory setting or just for simplici…
-
I am working with a use case where only camera path is required in a video. I do not want the sparse reconstruction. Is there a way to skip reconstruction to make the pipeline faster?
-
1.Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop(2019)
collaborate regression-based (as initial pose) and iterative optimization-based approach.
code: No
2.Weakly S…
-
Hello, thanks for your great work. Human Reconstruction results are pretty good on images and videos. Now I wonder how to convert the output of TokenHMR back to AMASS format?
B
I could get the **pre…
-
Hi, thanks for your great work. I have created depth and normal map for all the frames for my video. I want to create a 3d reconstruction from this video. Your depth_to_normal_map.py only takes an ima…