Get the latest tech news
3D Gaussian Splatting as Markov Chain Monte Carlo
Novel view reconstructions for (right) our method and (left) conventional 3D Gaussian Splatting with random initializations. Our method, even with random initialization, faithfully reconstructs the scene (e.g..
Our method, even with random initialization, faithfully reconstructs the scene (e.g.. buildings at the back and the ground texture) providing much higher quality renderings. We then rewrite the densification and pruning strategies in 3D Gaussian Splatting as simply a deterministic state transition of MCMC samples, removing these heuristics from the framework. On various standard evaluation scenes, we show that our method provides improved rendering quality, easy control over the number of Gaussians, and robustness to initialization.
Or read this on Hacker News
