“The paper is also on arXiv, which includes the TeX source. The experimental HTML view for this paper has automatic (internal) hyperlinks like hyperref: https://arxiv.org/abs/2404.09591 Edit: The TeX source has the `draft` option for hyperref that disabled hyperlinks in the produced pdf. External links to references aren't recoverable from the included ma…”
3D Gaussian Splatting as Markov Chain Monte Carlo
While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, which can lead to poor-quality renderings, and reliance on a good initialization. In this work, we rethink the set of 3D Gaussians as a random sample drawn from an underlying probability distribution describing the physical representation of the scene-in other words, Markov Chain Monte Carlo (MCMC) samples. Under this view, we show that the 3D Gaussian updates can be converted as Stochastic Gradient Langevin Dynamics (SGLD) updates by simply introducing noise. 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. To do so, we revise the 'cloning' of Gaussians into a relocalization scheme that approximately preserves sample probability. To encourage efficient use of Gaussians, we introduce a regularizer that promotes the removal of unused Gaussians. 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.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Thats quite a difficult question, given the large amount of methods (https://github.com/MrNeRF/awesome-3D-gaussian-splatting). I think "3D Gaussian Splatting as Markov Chain Monte Carlo" looks very promising, as it redesigns the training so that it is no longer dependent on the desification algorithm: https://arxiv.org/abs/2404.09591v1”