3D Gaussian Splatting-based Change Detection for Physical Object Rearrangement
TLDR: We estimate 3D object-level changes from two sets of unaligned RGB images using 3D Gaussian Splatting as the scene representation, enabling accurate recovery of shapes and pose changes of rearranged objects in cluttered environments within tens of seconds using sparse (as few as one) new images.
output.mp4
The 3DGS-CD dataset can be found here. All the RGB images have been pre-processed (i.e. downscaled and undistorted). Below is the structure of the data folder:
scene_name
-rgb: Pre-change images
-rgb_new: Post-change images
-rgb_eval: Evaluation images at novel post-change views
-masks_gt: Ground truth change masks for evaluation images
Our code will be released soon!