[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, and Vincent Sitzmann
I have two new datasets with RGB-D ground truth. But their camera movement speeds are different. I want to set different max_context_gap for each dataset. Do you know how to change your code and configuration for my purpose?
The easiest way would probably be to do some subsampling within the dataset (before the sampler is called), such that the movement speeds roughly line up.
I have two new datasets with RGB-D ground truth. But their camera movement speeds are different. I want to set different
max_context_gap
for each dataset. Do you know how to change your code and configuration for my purpose?