Get the latest tech news
Splatt3R: Zero-Shot Gaussian Splatting from Uncalibrated Image Pairs
Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
Following the spirit of MASt3R, we show that a simple modification to their architecture, alongside a well-chosen training loss, is sufficient to achieve strong novel view synthesis results. We introduce a third head to predict covariances (parameterized by rotation quaternions and scales), spherical harmonics, opacities and mean offsets for each point. Some of these target images may contain regions of the scene that were not visible to the two context views due to being obscured, or outside of their frustums.
Or read this on Hacker News